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

    Neuronpedia

    INDEX
    Explanations

    Negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _created
    -0.07
    ріш
    -0.06
    ực
    -0.06
    (schedule
    -0.06
    チェ
    -0.06
     websites
    -0.06
    portun
    -0.06
     解
    -0.06
     bà
    -0.06
     powdered
    -0.06
    POSITIVE LOGITS
    �
    0.08
     müc
    0.07
    _ES
    0.06
    лючается
    0.06
     перел
    0.06
    bé
    0.06
    _estimate
    0.06
     MUST
    0.06
     Primitive
    0.06
     pady
    0.06
    Act Density 0.049%

    No Known Activations