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

    Neuronpedia

    INDEX
    Explanations

    Non-English words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pump
    -0.07
     Pe
    -0.07
     bathrooms
    -0.07
    Continuous
    -0.07
    -mean
    -0.07
    -0.07
    23
    -0.07
    ků
    -0.07
     engaged
    -0.07
     часу
    -0.07
    POSITIVE LOGITS
    握
    0.06
     distint
    0.06
    .SM
    0.06
     тол
    0.06
     odak
    0.06
    ********
    0.05
    ,"%
    0.05
    ポート
    0.05
    .damage
    0.05
    ，而
    0.05
    Act Density 0.018%

    No Known Activations