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

    Neuronpedia

    INDEX
    Explanations

    wants and threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IFSC
    0.90
     año
    0.89
     kalau
    0.88
     akibat
    0.88
     celebró
    0.88
     dibawa
    0.88
     hambre
    0.87
    ى
    0.86
     bisa
    0.86
     profesional
    0.86
    POSITIVE LOGITS
    UCK
    0.82
    zetten
    0.79
    ья
    0.75
    oreal
    0.73
    ARD
    0.73
    い
    0.73
    URY
    0.72
    I
    0.72
    NO
    0.71
    ANGER
    0.71
    Act Density 0.001%

    No Known Activations