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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Savior
    -0.07
     aboard
    -0.07
     daß
    -0.07
     olanak
    -0.07
     clever
    -0.07
     عند
    -0.06
     Situation
    -0.06
     coarse
    -0.06
     completely
    -0.06
     quirky
    -0.06
    POSITIVE LOGITS
     catal
    0.07
    antee
    0.06
    Enh
    0.06
    zeich
    0.06
    "description
    0.06
    centaje
    0.06
    证券
    0.06
    Tier
    0.06
     strr
    0.06
    topic
    0.06
    Act Density 0.020%

    No Known Activations