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

    Neuronpedia

    INDEX
    Explanations

    tracks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drip
    -0.07
    従
    -0.07
     їй
    -0.06
    관련
    -0.06
    debian
    -0.06
    dims
    -0.06
    (word
    -0.06
    ơ
    -0.06
     Sug
    -0.06
     Fro
    -0.06
    POSITIVE LOGITS
     listening
    0.07
     scars
    0.06
    ución
    0.06
    .once
    0.06
     Gang
    0.06
     useful
    0.06
     pathology
    0.06
     كيل
    0.06
     PIXEL
    0.06
     Convert
    0.06
    Act Density 0.000%

    No Known Activations