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

    Neuronpedia

    INDEX
    Explanations

    severity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    แส
    -0.07
    286
    -0.07
     evenings
    -0.06
    775
    -0.06
    ูรณ
    -0.06
     месяца
    -0.06
    538
    -0.06
    ewan
    -0.06
    ensors
    -0.06
    LiveData
    -0.06
    POSITIVE LOGITS
    ือ
    0.07
    -ranked
    0.07
     lying
    0.07
    .Hit
    0.06
     relaxation
    0.06
    !="
    0.06
    halb
    0.06
     strong
    0.06
    ycling
    0.06
     communicated
    0.06
    Act Density 0.030%

    No Known Activations