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

    Neuronpedia

    INDEX
    Explanations

    sql declare statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    эф
    0.40
    яс
    0.39
    াস
    0.38
    თავ
    0.38
     utilizing
    0.38
     Utilizing
    0.37
     Dependency
    0.36
    ым
    0.36
    Collider
    0.36
    tolist
    0.35
    POSITIVE LOGITS
     Tym
    0.42
     بص
    0.38
     winters
    0.37
     Luci
    0.36
    ریشن
    0.36
     Teachers
    0.36
    afir
    0.36
    setcounter
    0.36
     spears
    0.36
     leggings
    0.36
    Act Density 0.000%

    No Known Activations