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

    Neuronpedia

    INDEX
    Explanations

    Game rules/instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bat
    -0.06
    ponential
    -0.06
    .stereotype
    -0.06
     pObj
    -0.06
    dan
    -0.06
    -stat
    -0.06
     Э
    -0.06
    MapView
    -0.06
    standard
    -0.06
    ("")
    -0.06
    POSITIVE LOGITS
     bikini
    0.07
     backup
    0.07
    ایان
    0.07
    NN
    0.06
     záb
    0.06
    ainter
    0.06
    Signal
    0.06
     ort
    0.06
    direction
    0.06
    SX
    0.06
    Act Density 0.015%

    No Known Activations