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

    Neuronpedia

    INDEX
    Explanations

    code, numbers, separators

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ieties
    -0.08
    zoals
    -0.08
     ferrovi
    -0.08
    enaars
    -0.08
     dokon
    -0.08
    jež
    -0.07
     beperkt
    -0.07
    _updates
    -0.07
     duurzaam
    -0.07
    ář
    -0.07
    POSITIVE LOGITS
    шую
    0.08
     presenting
    0.08
     présentant
    0.08
     unbek
    0.08
     chromosomes
    0.07
     calma
    0.07
     IMF
    0.07
    landa
    0.07
     scared
    0.07
    /window
    0.07
    Act Density 0.000%

    No Known Activations