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

    Neuronpedia

    INDEX
    Explanations

    causes of problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ST
    -0.07
    _FAST
    -0.06
    mekte
    -0.06
     TA
    -0.06
    KH
    -0.06
     Wak
    -0.06
    _stop
    -0.06
     urinary
    -0.06
     sợ
    -0.06
    OU
    -0.06
    POSITIVE LOGITS
    moz
    0.07
    marsh
    0.07
    .Int
    0.06
     localObject
    0.06
     winter
    0.06
     シ
    0.06
     prefers
    0.06
    줄
    0.06
     etk
    0.06
     curly
    0.06
    Act Density 0.266%

    No Known Activations