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

    Neuronpedia

    INDEX
    Explanations

    combining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sequence
    -0.08
    .strict
    -0.08
     Stops
    -0.07
    Contains
    -0.06
    versed
    -0.06
    Tracking
    -0.06
    unbind
    -0.06
    θεί
    -0.06
    -only
    -0.06
    isons
    -0.06
    POSITIVE LOGITS
    окси
    0.06
     yar
    0.06
    ！');↵
    0.06
    clerosis
    0.06
    ).[
    0.06
    orama
    0.06
    itational
    0.06
    (lock
    0.06
    γραμμα
    0.06
     irc
    0.06
    Act Density 0.067%

    No Known Activations