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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inşa
    -0.06
     '|'
    -0.06
    _SERIAL
    -0.06
    Effective
    -0.06
    .Linear
    -0.06
     Cycl
    -0.06
     lith
    -0.06
     Delegate
    -0.06
     Principle
    -0.06
    Token
    -0.06
    POSITIVE LOGITS
    still
    0.07
    comfort
    0.07
    regist
    0.06
    bruar
    0.06
    kanı
    0.06
     unlock
    0.06
    Keeper
    0.06
    ouis
    0.06
    اعب
    0.06
     �
    0.06
    Act Density 0.070%

    No Known Activations