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

    Neuronpedia

    INDEX
    Explanations

    measurements, numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autofocus
    -0.06
    сам
    -0.06
     weakening
    -0.06
    	email
    -0.06
    labilir
    -0.06
    CLU
    -0.06
    深圳
    -0.06
     パ
    -0.06
    .invalid
    -0.06
    式会社
    -0.06
    POSITIVE LOGITS
    列
    0.07
     }(
    0.07
     tailor
    0.06
     gusta
    0.06
    ходит
    0.06
     mír
    0.06
     omega
    0.06
     Establish
    0.06
    Trace
    0.06
    expense
    0.06
    Act Density 0.082%

    No Known Activations