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

    Neuronpedia

    INDEX
    Explanations

    correctness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کل
    -0.06
     NYT
    -0.06
    _classifier
    -0.06
    gment
    -0.06
    (json
    -0.06
    chest
    -0.06
    灵
    -0.06
     deposited
    -0.06
     contacts
    -0.06
     drill
    -0.06
    POSITIVE LOGITS
    egral
    0.07
    .Raycast
    0.07
     creo
    0.06
     thirds
    0.06
    minecraft
    0.06
    /{}/
    0.06
    ahrung
    0.06
     Eine
    0.06
     kişilerin
    0.06
     lk
    0.06
    Act Density 0.003%

    No Known Activations