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

    Neuronpedia

    INDEX
    Explanations

    floating or upwards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ш
    2.14
    про
    2.13
    е
    2.11
    ד
    2.05
    р
    2.00
    ст
    1.95
    ре
    1.82
    си
    1.82
    ва
    1.80
    -
    1.80
    POSITIVE LOGITS
    驒
    1.95
    parseFloat
    1.89
    させ
    1.85
    ॅमिली
    1.77
    させる
    1.77
     жив
    1.72
    िक
    1.69
     chảy
    1.69
    द्योगिकी
    1.64
     जरिये
    1.61
    Act Density 0.207%

    No Known Activations