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

    Neuronpedia

    INDEX
    Explanations

    Key explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Inspection
    0.72
     derail
    0.69
     unset
    0.64
    侓
    0.63
     Division
    0.63
     Divided
    0.62
    oline
    0.62
     inspections
    0.62
    ौली
    0.61
     Sna
    0.60
    POSITIVE LOGITS
    кей
    0.76
    kej
    0.75
    袈
    0.73
    кий
    0.73
     kock
    0.71
    kata
    0.71
    gloss
    0.70
     लिहा
    0.69
     העולם
    0.68
    itiis
    0.68
    Act Density 0.026%

    No Known Activations