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

    Neuronpedia

    INDEX
    Explanations

    had in mind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    1.88
    يا
    1.70
    ،
    1.59
    ABLE
    1.56
     mô
    1.54
     royalties
    1.52
     majd
    1.51
     situés
    1.50
     robbery
    1.48
     hearsay
    1.48
    POSITIVE LOGITS
    s
    2.50
    ج
    2.05
     volna
    2.02
    ant
    1.99
    ों
    1.92
    ین
    1.92
     anteriormente
    1.88
    ar
    1.85
    gum
    1.85
    sig
    1.83
    Act Density 0.164%

    No Known Activations