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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    orizontal
    -0.07
    を
    -0.07
     clothing
    -0.07
     articulated
    -0.06
    _learning
    -0.06
    .enter
    -0.06
     olarak
    -0.06
    _conditions
    -0.06
    тя
    -0.06
    　 　 　 　
    -0.06
    POSITIVE LOGITS
    Criterion
    0.06
    cf
    0.06
     McCorm
    0.06
     �
    0.06
     doctr
    0.06
     buttonWithType
    0.06
     Dome
    0.06
     Compatible
    0.06
     arising
    0.05
    (interval
    0.05
    Act Density 0.041%

    No Known Activations