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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -h
    -0.07
    699
    -0.07
    689
    -0.07
    ософ
    -0.07
    649
    -0.07
    designation
    -0.07
    364
    -0.07
     أغسطس
    -0.07
     itself
    -0.07
     philosophers
    -0.06
    POSITIVE LOGITS
     :
    0.07
     заст
    0.06
     edilen
    0.06
     tato
    0.06
     General
    0.06
    kat
    0.06
     pageCount
    0.06
    .PI
    0.06
     intercept
    0.06
     raj
    0.06
    Act Density 0.005%

    No Known Activations