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

    Neuronpedia

    INDEX
    Explanations

    ensemble

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    modify
    -0.07
     entrar
    -0.07
    enden
    -0.07
    _chunk
    -0.06
     chips
    -0.06
     cx
    -0.06
     chip
    -0.06
     Wilson
    -0.06
     نار
    -0.06
     fc
    -0.06
    POSITIVE LOGITS
     πολι
    0.08
    $type
    0.07
    imps
    0.06
     Twice
    0.06
    最近
    0.06
    食べ
    0.06
    至
    0.06
    .DateTime
    0.06
     Asked
    0.06
     Politico
    0.06
    Act Density 0.001%

    No Known Activations