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

    Neuronpedia

    INDEX
    Explanations

    strength, Campaign

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IZONTAL
    2.13
    क
    1.83
    🫣
    1.69
     méridionale
    1.64
    🥸
    1.63
    かもし
    1.62
    ்
    1.61
    ../../../
    1.57
    かも
    1.53
    ശാസ്ത്ര
    1.52
    POSITIVE LOGITS
    fpr
    1.78
    motivation
    1.65
    ین
    1.64
    цию
    1.60
    ार
    1.51
    ionate
    1.42
    getId
    1.41
     conformation
    1.39
    нга
    1.36
    ipton
    1.34
    Act Density 0.140%

    No Known Activations