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

    Neuronpedia

    INDEX
    Explanations

    Places

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CRE
    -0.07
    Color
    -0.06
     called
    -0.06
    --)
↵
    -0.06
    125
    -0.06
    わせ
    -0.06
    ział
    -0.06
     stripslashes
    -0.06
    _dd
    -0.06
    TextInput
    -0.06
    POSITIVE LOGITS
     Rename
    0.07
     Ven
    0.07
     Yankees
    0.06
    average
    0.06
     average
    0.06
     Dit
    0.06
     قن
    0.06
    激
    0.06
     Barrier
    0.06
    _fds
    0.06
    Act Density 0.002%

    No Known Activations