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

    Neuronpedia

    INDEX
    Explanations

    withdrawal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     APC
    -0.07
    ける
    -0.07
    模式
    -0.07
    autop
    -0.07
     Somerset
    -0.07
    けた
    -0.07
     optimizing
    -0.07
    iset
    -0.06
     environments
    -0.06
     conseg
    -0.06
    POSITIVE LOGITS
     withdrawal
    0.07
     khỏ
    0.07
     td
    0.07
    ("</
    0.06
    hung
    0.06
    toggleClass
    0.06
     lex
    0.06
    rol
    0.06
     landlord
    0.06
     HEL
    0.06
    Act Density 0.001%

    No Known Activations