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

    Neuronpedia

    INDEX
    Explanations

    quoted variables or paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cyl
    2.23
    leşt
    1.93
    или
    1.89
    orage
    1.75
     assailant
    1.74
    incorrect
    1.73
    osing
    1.71
     acel
    1.71
    قوق
    1.68
    ية
    1.68
    POSITIVE LOGITS
    swald
    2.25
    ुका
    1.98
    teni
    1.94
    ς
    1.94
    uità
    1.90
    řich
    1.82
    াস
    1.74
    track
    1.72
    Track
    1.70
    प्तान
    1.68
    Act Density 0.240%

    No Known Activations