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

    Neuronpedia

    INDEX
    Explanations

    any other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    1.05
    ent
    0.92
    ر
    0.88
    ர்
    0.83
    gi
    0.80
     beginners
    0.79
     (*)
    0.78
    <0xAD>
    0.78
    ick
    0.78
    伶
    0.77
    POSITIVE LOGITS
    ă
    1.22
    okhlov
    1.12
    ClFN
    1.12
     filóso
    1.09
    AY
    1.05
     озера
    1.04
    蚪
    1.04
    AZ
    1.00
    ногда
    0.99
    ం
    0.97
    Act Density 0.002%

    No Known Activations