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

    Neuronpedia

    INDEX
    Explanations

    power plant emissions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    agan
    -0.07
    уча
    -0.07
     Pag
    -0.07
    同一
    -0.07
     Appeal
    -0.06
     Success
    -0.06
     Reconstruction
    -0.06
     sin
    -0.06
     usage
    -0.06
    得分
    -0.06
    POSITIVE LOGITS
    venient
    0.07
    reatest
    0.07
    老妈
    0.07
    _markup
    0.07
     //'
    0.07
    곸
    0.06
    뎈
    0.06
    elleicht
    0.06
    locals
    0.06
    Quantity
    0.06
    Act Density 0.021%

    No Known Activations