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

    Neuronpedia

    INDEX
    Explanations

    conversational starters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     There
    1.11
     Here
    1.04
     there
    1.01
     Unfortunately
    0.98
     What
    0.98
     Let
    0.97
     Admittedly
    0.95
     இந்தக்
    0.94
     Isn
    0.93
     pergunt
    0.91
    POSITIVE LOGITS
    Hi
    0.77
    web
    0.68
    HI
    0.65
    Http
    0.64
    (:
    0.64
    hi
    0.62
    ahana
    0.61
    راجعه
    0.61
     lainnya
    0.61
    g
    0.60
    Act Density 0.222%

    No Known Activations