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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    spo
    -0.08
     UIImage
    -0.07
     áreas
    -0.06
    otta
    -0.06
     Executor
    -0.06
    azione
    -0.06
    PEndPoint
    -0.06
    (ids
    -0.06
     additives
    -0.06
    nictví
    -0.06
    POSITIVE LOGITS
    Much
    0.07
     energetic
    0.07
    ()])↵
    0.07
    .semantic
    0.06
     mindful
    0.06
     Kendall
    0.06
     representing
    0.06
     Enter
    0.06
     #↵
    0.06
     joined
    0.06
    Act Density 0.000%

    No Known Activations