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

    Neuronpedia

    INDEX
    Explanations

    references to specific individuals and associated objects or properties

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

    names and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.89
     propOrder
    -0.86
    \{\\
    -0.79
    ########.
    -0.72
     dAtA
    -0.72
     '\\;'
    -0.67
    脚注の使い方
    -0.65
    RegressionTest
    -0.65
     <<<<<<<<<<<<<<
    -0.63
    Tembelea
    -0.62
    POSITIVE LOGITS
    Referensi
    0.37
    ushka
    0.36
    post
    0.35
     Hasbro
    0.35
     post
    0.35
     Originals
    0.34
    TabStop
    0.33
     Gron
    0.32
    bul
    0.32
    4
    0.31
    Act Density 0.010%

    No Known Activations