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

    Neuronpedia

    INDEX
    Explanations

    Physics and statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nachricht
    -0.07
     आक
    -0.07
    _pick
    -0.07
     Sovere
    -0.07
    력
    -0.06
    .advance
    -0.06
    _trade
    -0.06
    ake
    -0.06
     слово
    -0.06
    ]")]↵
    -0.06
    POSITIVE LOGITS
    ICES
    0.07
     Ginger
    0.06
    (ax
    0.06
    iceps
    0.06
    TXT
    0.06
    	const
    0.06
    去了
    0.06
    delimiter
    0.06
     onion
    0.06
    [this
    0.06
    Act Density 0.004%

    No Known Activations