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

    Neuronpedia

    INDEX
    Explanations

    say exclamation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     […]...↵
    -0.06
    ？
    -0.06
    (BigDecimal
    -0.06
    تیب
    -0.06
    íc
    -0.06
     accompanies
    -0.06
    inel
    -0.06
    andoned
    -0.06
    ابعة
    -0.06
    stin
    -0.05
    POSITIVE LOGITS
    edges
    0.07
    .view
    0.07
     Beats
    0.07
     �
    0.06
    _auth
    0.06
    .Comp
    0.06
     ballots
    0.06
     MacOS
    0.06
     exports
    0.06
    _FALSE
    0.06
    Act Density 0.000%

    No Known Activations