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

    Neuronpedia

    INDEX
    Explanations

    elaborate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     achie
    -0.07
    _ab
    -0.06
    resultado
    -0.06
    (ti
    -0.06
    -IN
    -0.06
    dados
    -0.06
     passages
    -0.06
     빠
    -0.06
     preserves
    -0.06
     Jung
    -0.06
    POSITIVE LOGITS
    点
    0.07
    صب
    0.07
     hone
    0.07
    coming
    0.06
     点
    0.06
    Coming
    0.06
    س
    0.06
    Specify
    0.06
    番
    0.06
     lodging
    0.06
    Act Density 0.015%

    No Known Activations