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

    Neuronpedia

    INDEX
    Explanations

    start of model response "Okay,"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    二是
    0.73
     Pfaff
    0.61
    porter
    0.59
     тө
    0.59
    pedo
    0.58
     firefighters
    0.58
     quadrat
    0.58
    peda
    0.57
     firefighting
    0.57
    quark
    0.56
    POSITIVE LOGITS
    ｗ
    0.58
    wipe
    0.55
    కాశ
    0.54
    wound
    0.53
    Skip
    0.53
    减
    0.52
    律
    0.50
    Attr
    0.50
    வுகளில்
    0.49
    ไม่ต้อง
    0.49
    Act Density 0.160%

    No Known Activations