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

    Neuronpedia

    INDEX
    Explanations

    dime novels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gør
    0.41
     كلا
    0.37
     expands
    0.36
     attains
    0.36
    ota
    0.36
    Some
    0.35
    Laur
    0.35
    Uns
    0.35
    man
    0.35
    Relations
    0.35
    POSITIVE LOGITS
     summarised
    0.40
    трен
    0.38
     Бы
    0.38
     Update
    0.37
    hattisgarh
    0.37
    墳
    0.36
     srand
    0.36
    کرو
    0.35
    ccgi
    0.35
    多
    0.35
    Act Density 0.000%

    No Known Activations