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

    Neuronpedia

    INDEX
    Explanations

    decision

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    世
    -0.07
     THE
    -0.06
     стоит
    -0.06
    ARNING
    -0.06
     метою
    -0.06
    能力
    -0.06
    OMETRY
    -0.06
    .getUrl
    -0.06
    ením
    -0.06
     VALID
    -0.06
    POSITIVE LOGITS
     reducers
    0.08
     calculates
    0.06
    0.06
     eventual
    0.06
    elines
    0.06
     rely
    0.06
     Hurricane
    0.06
     Benny
    0.06
     khô
    0.06
     Kab
    0.06
    Act Density 0.013%

    No Known Activations