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

    Neuronpedia

    INDEX
    Explanations

    development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tooltip
    -0.06
    _FIRST
    -0.06
     şarkı
    -0.06
    越
    -0.06
     Tooltip
    -0.06
     tú
    -0.06
     essere
    -0.06
     FormData
    -0.06
     muito
    -0.06
     Needle
    -0.06
    POSITIVE LOGITS
     reinforcements
    0.07
     plugs
    0.07
    μήμα
    0.07
    LEMENT
    0.07
    Responses
    0.06
    ewhere
    0.06
    arter
    0.06
    �
    0.06
    šker
    0.06
     Dexter
    0.06
    Act Density 0.002%

    No Known Activations