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

    Neuronpedia

    INDEX
    Explanations

    national helpline

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    魅
    0.62
     चीज़
    0.59
     Principle
    0.58
     المهم
    0.58
    hetically
    0.57
    oning
    0.57
    ClickListener
    0.56
     menjal
    0.55
     essent
    0.55
    현
    0.55
    POSITIVE LOGITS
    pline
    0.99
    INE
    0.91
    Ine
    0.86
    돠
    0.86
    INES
    0.84
     Bxe
    0.84
    ینی
    0.83
     curves
    0.82
    Tobacco
    0.81
    ROWN
    0.80
    Act Density 0.003%

    No Known Activations