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

    Neuronpedia

    INDEX
    Explanations

    destruction and negative outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     những
    0.68
     صارفین
    0.57
     questo
    0.55
    那些
    0.54
     ragazzi
    0.54
     ambayo
    0.54
     camere
    0.54
     lettera
    0.53
     Mitch
    0.52
     intelligente
    0.52
    POSITIVE LOGITS
     zerstört
    0.54
                      
    0.52
     ブレスレット
    0.45
     sexu
    0.44
     (†
    0.43
     /=
    0.43
    ANSWER
    0.42
    ABET
    0.42
     أو
    0.42
     다르
    0.41
    Act Density 0.079%

    No Known Activations