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

    Neuronpedia

    INDEX
    Explanations

    lead

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ANDARD
    -0.06
    .DELETE
    -0.06
     ideally
    -0.06
     landmarks
    -0.06
     œ
    -0.06
     وضع
    -0.06
    ETERS
    -0.06
     pickle
    -0.06
    Cou
    -0.06
    .UndefOr
    -0.06
    POSITIVE LOGITS
    ันยายน
    0.06
     Completion
    0.06
    ([$
    0.06
    uckle
    0.06
    -www
    0.06
    ญ
    0.06
    IAM
    0.06
     jos
    0.06
    (jLabel
    0.06
    faith
    0.06
    Act Density 0.226%

    No Known Activations