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

    Neuronpedia

    INDEX
    Explanations

    percentages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Brooklyn
    -0.07
    抜
    -0.07
    、新
    -0.06
     Courage
    -0.06
    艺
    -0.06
     Situation
    -0.06
    .Unmarshal
    -0.06
    ochen
    -0.05
     khỏi
    -0.05
    rotch
    -0.05
    POSITIVE LOGITS
     acclaimed
    0.07
     SWAT
    0.07
     К
    0.07
    }></
    0.06
    unan
    0.06
     Παν
    0.06
    -ranking
    0.06
     hbox
    0.06
    в
    0.06
    ltr
    0.06
    Act Density 0.008%

    No Known Activations