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

    Neuronpedia

    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buscar
    -0.07
    tracking
    -0.07
    ZW
    -0.06
     carro
    -0.06
     slain
    -0.06
     bullying
    -0.06
    ifie
    -0.06
    "data
    -0.06
    keleton
    -0.06
    ifies
    -0.06
    POSITIVE LOGITS
    (Intent
    0.07
    __));↵
    0.07
    .setTitle
    0.07
     sở
    0.06
    ΑΝ
    0.06
     affiliation
    0.06
    ----------------------------------------------------------------------↵
    0.06
     anders
    0.06
    دي
    0.06
    ्द
    0.06
    Act Density 0.016%

    No Known Activations