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

    Neuronpedia

    INDEX
    Explanations

    brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     afterwards
    -0.07
    Charsets
    -0.07
    .Locale
    -0.07
     Parkinson
    -0.07
     provided
    -0.07
     stora
    -0.07
     verr
    -0.07
     PDO
    -0.07
    PDO
    -0.07
     Botox
    -0.07
    POSITIVE LOGITS
     depicts
    0.10
     возле
    0.10
     Szene
    0.10
     davant
    0.09
     সামনে
    0.09
     scena
    0.09
     രംഗ
    0.09
    畫
    0.09
     protagonista
    0.09
     腾
    0.09
    Act Density 0.061%

    No Known Activations