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

    Neuronpedia

    INDEX
    Explanations

    warnings of downsides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reading
    -0.07
    ﻴ
    -0.07
    anca
    -0.07
    _rot
    -0.06
     휴
    -0.06
    мар
    -0.06
    268
    -0.06
    dismiss
    -0.06
     translucent
    -0.06
    28
    -0.06
    POSITIVE LOGITS
     manifests
    0.07
    QUAL
    0.07
     THEN
    0.07
    аторы
    0.06
    ium
    0.06
    Sink
    0.06
    cond
    0.06
     thresholds
    0.06
     stringstream
    0.06
    (withDuration
    0.06
    Act Density 0.069%

    No Known Activations