Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    specific named entities, particularly titles of creative works and notable subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows punctuation or special characters

    np_acts-logits-general · gemini-2.0-flash

    that followed by punctuation or symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ResumeLayout
    -0.91
     <<<<<<<<<<<<<<
    -0.85
     malheure
    -0.83
    ISupport
    -0.82
     AssemblyCulture
    -0.81
    tableFuture
    -0.80
     chré
    -0.80
     ainfi
    -0.79
     saveiro
    -0.79
    Portale
    -0.79
    POSITIVE LOGITS
     G
    0.73
     N
    0.73
     Z
    0.71
     D
    0.69
     X
    0.68
     P
    0.66
     T
    0.66
     B
    0.65
     K
    0.65
     M
    0.63
    Act Density 0.582%

    No Known Activations