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

    Neuronpedia

    INDEX
    Explanations

    present / actual / current

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MUS
    1.34
    LIN
    1.29
    MOS
    1.24
    G
    1.24
    M
    1.20
    MEM
    1.16
    𝓭
    1.16
    WAS
    1.10
     juggle
    1.05
    GRA
    1.05
    POSITIVE LOGITS
    ти
    1.54
    ре
    1.23
    ла
    1.22
    ล
    1.20
    ва
    1.05
    *
    1.05
    ?
    0.99
    ции
    0.98
    ра
    0.97
    ור
    0.94
    Act Density 0.000%

    No Known Activations