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

    Neuronpedia

    INDEX
    Explanations

    Charsets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _corners
    -0.07
     cravings
    -0.07
     �
    -0.06
    нож
    -0.06
     nesting
    -0.06
     dům
    -0.06
    spoken
    -0.06
    δας
    -0.06
     Reb
    -0.06
     rawData
    -0.06
    POSITIVE LOGITS
    ufacturer
    0.07
    ofire
    0.07
     Observable
    0.07
     glue
    0.06
    ige
    0.06
    |↵
    0.06
    <Role
    0.06
    μενο
    0.06
    ered
    0.06
    "user
    0.06
    Act Density 0.000%

    No Known Activations