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

    Neuronpedia

    INDEX
    Explanations

    punctuations and special characters

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

    user commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.94
    onAttach
    -0.71
    findpost
    -0.70
     contextLoads
    -0.65
     Administrativna
    -0.63
     betweenstory
    -0.63
    StructEnd
    -0.62
    rungsseite
    -0.61
    EndContext
    -0.60
    出版年
    -0.59
    POSITIVE LOGITS
     was
    0.43
     used
    0.39
     walked
    0.38
     depress
    0.38
     inserted
    0.38
     pulled
    0.37
     is
    0.37
     supported
    0.36
     strongly
    0.36
     partially
    0.35
    Act Density 0.007%

    No Known Activations