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

    Neuronpedia

    INDEX
    Explanations

    identical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ן
    1.67
    at
    1.58
    ני
    1.38
    I
    1.36
    ו
    1.36
    서
    1.34
    ।
    1.27
     I
    1.25
     that
    1.19
     with
    1.15
    POSITIVE LOGITS
    ва
    1.31
    ன்
    1.23
    ેશ
    1.21
    ill
    1.10
    és
    1.09
    ित
    1.07
    esség
    1.05
    ாக
    1.05
    íme
    1.05
    ících
    0.98
    Act Density 0.000%

    No Known Activations