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
     acest
    -0.07
     Boy
    -0.07
     hebben
    -0.07
     labor
    -0.06
     funding
    -0.06
     averages
    -0.06
     pursue
    -0.06
     circuit
    -0.06
     Differential
    -0.06
    tx
    -0.06
    POSITIVE LOGITS
    PostExecute
    0.07
     onemocnění
    0.07
    _________________↵↵
    0.07
    !"↵
    0.07
    (Rect
    0.06
    Edited
    0.06
     неприят
    0.06
     uygulan
    0.06
    (&$
    0.06
    ('''
    0.06
    Act Density 0.029%

    No Known Activations