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

    Neuronpedia

    INDEX
    Explanations

    Questions/options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    料無料
    -0.07
    (Be
    -0.06
    OfSize
    -0.06
    gL
    -0.06
     borderBottom
    -0.06
     sobre
    -0.06
    unnel
    -0.06
    айд
    -0.06
    .»
    -0.05
    叶
    -0.05
    POSITIVE LOGITS
     savage
    0.06
    iffs
    0.06
     african
    0.06
    Food
    0.06
    ncy
    0.06
     Press
    0.06
    .map
    0.06
     Olympic
    0.06
     criminal
    0.06
     shooting
    0.06
    Act Density 0.333%

    No Known Activations