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

    Neuronpedia

    INDEX
    Explanations

    LaTeX/code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    insert
    -0.06
    	kfree
    -0.06
    adia
    -0.06
    .currentIndex
    -0.06
     ])↵↵
    -0.06
     infected
    -0.06
    lung
    -0.06
    fprintf
    -0.06
     harassed
    -0.06
    OND
    -0.06
    POSITIVE LOGITS
     曰
    0.07
     Virgin
    0.07
     viol
    0.07
    850
    0.06
     resulting
    0.06
    icro
    0.06
    187
    0.06
    589
    0.06
     Whole
    0.06
     微
    0.06
    Act Density 0.002%

    No Known Activations