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

    Neuronpedia

    INDEX
    Explanations

    lib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Threat
    -0.07
    Supplier
    -0.07
    dateTime
    -0.07
     журн
    -0.06
    ')),
    -0.06
    _PATH
    -0.06
    )에
    -0.06
    {{$
    -0.06
     multipart
    -0.06
     shortcuts
    -0.06
    POSITIVE LOGITS
    щина
    0.07
    -final
    0.06
     performed
    0.06
    	BIT
    0.06
     performs
    0.06
    반
    0.06
    (ti
    0.06
     Çin
    0.06
     Renault
    0.06
     resilient
    0.06
    Act Density 0.003%

    No Known Activations