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

    Neuronpedia

    INDEX
    Explanations

    career

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wishing
    -0.07
    .into
    -0.07
    _D
    -0.07
    _ad
    -0.07
    .K
    -0.07
    nn
    -0.06
    产业集聚
    -0.06
     MET
    -0.06
    Recipient
    -0.06
     propensity
    -0.06
    POSITIVE LOGITS
    𝕠
    0.07
    шу
    0.07
    (auth
    0.07
    బ
    0.07
     plainly
    0.07
    ള
    0.06
    威廉
    0.06
    ✯
    0.06
    kaza
    0.06
    кий
    0.06
    Act Density 0.008%

    No Known Activations