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

    Neuronpedia

    INDEX
    Explanations

    guidance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stereotypes
    -0.07
     implementation
    -0.06
     증가
    -0.06
     refin
    -0.06
     Straw
    -0.06
     projects
    -0.06
    ίες
    -0.06
     боку
    -0.06
    :return
    -0.06
     hashtags
    -0.06
    POSITIVE LOGITS
    irut
    0.07
    Ace
    0.06
    (ht
    0.06
     zh
    0.06
    erokee
    0.06
    BagConstraints
    0.06
    _BREAK
    0.06
    ruitment
    0.06
    joining
    0.06
    querque
    0.06
    Act Density 0.159%

    No Known Activations