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

    Neuronpedia

    INDEX
    Explanations

    child sexual abuse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Norm
    0.41
    sev
    0.39
     NOK
    0.38
     Hock
    0.37
    rabbit
    0.36
    Sev
    0.35
    Norm
    0.35
    äk
    0.35
     Exotic
    0.34
     Fe
    0.34
    POSITIVE LOGITS
     hers
    0.39
     slack
    0.38
    㽡
    0.38
    вища
    0.38
     pans
    0.37
    जू
    0.37
    躋
    0.37
     owning
    0.36
    útbol
    0.36
     Hers
    0.36
    Act Density 0.000%

    No Known Activations