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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     profess
    -0.07
    .GetName
    -0.07
     прог
    -0.07
    /tree
    -0.07
     serpent
    -0.07
    莺
    -0.07
     אף
    -0.07
    ѻ
    -0.07
    овое
    -0.07
    aussian
    -0.06
    POSITIVE LOGITS
    (B
    0.08
    .delta
    0.07
    市场的
    0.07
    dued
    0.07
    \">"
    0.07
    휄
    0.06
    	the
    0.06
    히
    0.06
    였다
    0.06
    _PUT
    0.06
    Act Density 0.001%

    No Known Activations