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

    Neuronpedia

    INDEX
    Explanations

    to find or learn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -"
    0.68
    -\
    0.65
    {};
    0.64
    fas
    0.62
    alerts
    0.61
    ()=>{
    0.60
    {}",
    0.60
    ل
    0.59
    getP
    0.59
    fatal
    0.57
    POSITIVE LOGITS
    िक
    0.68
     veg
    0.62
     disponibili
    0.61
     ragazzi
    0.61
    öger
    0.58
    נט
    0.58
     thawed
    0.57
    یک
    0.57
    صه
    0.56
     위해
    0.56
    Act Density 0.005%

    No Known Activations