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

    Neuronpedia

    INDEX
    Explanations

    crisis text line HOME

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tercera
    0.75
     third
    0.64
     मृत्यु
    0.61
     تیس
    0.59
     Imp
    0.58
     బా
    0.58
     arbitrage
    0.57
    MediaPath
    0.57
    Dial
    0.56
    third
    0.56
    POSITIVE LOGITS
    🦦
    0.65
    QT
    0.64
     clor
    0.61
    ையம்
    0.60
    Status
    0.59
     NTT
    0.58
    टीसी
    0.58
     status
    0.56
    ification
    0.55
    𝓗
    0.54
    Act Density 0.169%

    No Known Activations