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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     المل
    -0.07
    hound
    -0.07
    ags
    -0.07
    .before
    -0.07
    _dd
    -0.07
     hned
    -0.07
    建设
    -0.06
     ifdef
    -0.06
     mafia
    -0.06
    /ad
    -0.06
    POSITIVE LOGITS
    	Check
    0.07
     naï
    0.06
    dated
    0.06
    ……………………
    0.06
     etc
    0.06
    吾
    0.06
    كي
    0.06
     gri
    0.06
    HY
    0.06
    accuracy
    0.06
    Act Density 0.020%

    No Known Activations