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

    Neuronpedia

    INDEX
    Explanations

    cup

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('/
    -0.08
     ACA
    -0.07
    (ctrl
    -0.07
     Ради
    -0.07
    tyard
    -0.06
     lại
    -0.06
    ilin
    -0.06
    Filtered
    -0.06
    InputGroup
    -0.06
     Gareth
    -0.06
    POSITIVE LOGITS
    जन
    0.07
     tornado
    0.06
     farther
    0.06
     Hou
    0.06
     مدیر
    0.06
    सम
    0.06
    _house
    0.06
    mouseup
    0.06
    auc
    0.06
     Hutch
    0.06
    Act Density 0.003%

    No Known Activations