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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     EVENTS
    -0.07
     CAST
    -0.07
    ucus
    -0.07
    lose
    -0.06
    .gradient
    -0.06
     freely
    -0.06
     vlastně
    -0.06
     INT
    -0.06
    Shows
    -0.06
     distinctly
    -0.06
    POSITIVE LOGITS
    Edition
    0.08
    Authorized
    0.07
    [result
    0.07
    егодня
    0.06
    ")))↵
    0.06
    -dark
    0.06
    Mur
    0.06
     edits
    0.06
    _strlen
    0.06
    дя
    0.06
    Act Density 0.043%

    No Known Activations