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

    Neuronpedia

    INDEX
    Explanations

    ization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _reads
    -0.07
     депут
    -0.07
     أغ
    -0.06
     blob
    -0.06
     政
    -0.06
    (w
    -0.06
    ิลป
    -0.06
     oc
    -0.06
    (Resource
    -0.06
    损
    -0.06
    POSITIVE LOGITS
     Mills
    0.07
     Inside
    0.06
    ien
    0.06
    oward
    0.06
    ising
    0.06
    upert
    0.06
     Psychological
    0.06
     fixing
    0.06
    buyer
    0.06
     sleeps
    0.06
    Act Density 0.003%

    No Known Activations