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

    Neuronpedia

    INDEX
    Explanations

    describing places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reproductive
    -0.07
    inal
    -0.07
    魚
    -0.07
    ao
    -0.07
    알
    -0.07
    AMB
    -0.06
    ignet
    -0.06
    #a
    -0.06
    Це
    -0.06
    玛
    -0.06
    POSITIVE LOGITS
     Apart
    0.06
     Usage
    0.06
     charged
    0.06
     outsiders
    0.06
    Len
    0.06
     rendered
    0.06
    @extends
    0.06
     titulo
    0.06
     achieve
    0.06
    dsn
    0.06
    Act Density 0.043%

    No Known Activations