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

    Neuronpedia

    INDEX
    Explanations

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    textView
    -0.06
    MMM
    -0.06
    vecs
    -0.06
    Evt
    -0.06
    ollipop
    -0.05
     kend
    -0.05
     southern
    -0.05
    こんに
    -0.05
    吴
    -0.05
    وزی
    -0.05
    POSITIVE LOGITS
     capacity
    0.07
     Plaint
    0.07
     avan
    0.07
     bulky
    0.07
    upert
    0.07
     states
    0.07
     salary
    0.07
    Ellipse
    0.07
    olog
    0.07
     централь
    0.07
    Act Density 0.000%

    No Known Activations