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

    Neuronpedia

    INDEX
    Explanations

    ont

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    skirts
    -0.06
     mice
    -0.06
    Todd
    -0.06
    ewidth
    -0.06
     věci
    -0.06
     inheritance
    -0.06
    acles
    -0.06
     sturdy
    -0.06
     swear
    -0.06
    solve
    -0.05
    POSITIVE LOGITS
    „J
    0.07
    .Dense
    0.07
    .BASE
    0.07
    بالإنجليزية
    0.07
    .Common
    0.07
    getSession
    0.07
     useHistory
    0.06
     จ
    0.06
    _CS
    0.06
     содерж
    0.06
    Act Density 0.019%

    No Known Activations