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

    Neuronpedia

    INDEX
    Explanations

    Child protective services

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     typo
    -0.09
    객
    -0.09
     multiplication
    -0.08
     ć
    -0.08
     nautical
    -0.08
    002
    -0.08
     jok
    -0.07
     cosine
    -0.07
     turb
    -0.07
     tedious
    -0.07
    POSITIVE LOGITS
     custody
    0.09
     grandparents
    0.09
    福利
    0.09
     квали
    0.08
     allegations
    0.08
    classified
    0.08
     нарушения
    0.08
     Classified
    0.08
     violations
    0.08
     случаях
    0.08
    Act Density 0.040%

    No Known Activations