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

    Neuronpedia

    INDEX
    Explanations

    Paying and costs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    x
    -0.08
     rocking
    -0.07
    .WRAP
    -0.07
    ................................
    -0.06
     is
    -0.06
     blockade
    -0.06
     низ
    -0.06
    asl
    -0.06
     caps
    -0.06
    学校
    -0.06
    POSITIVE LOGITS
    ώνα
    0.08
    ็นต
    0.06
    -kit
    0.06
     گل
    0.06
    sensor
    0.06
    _Word
    0.06
    ,alpha
    0.06
    otent
    0.06
    experiment
    0.06
    ushort
    0.06
    Act Density 0.014%

    No Known Activations