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

    Neuronpedia

    INDEX
    Explanations

    summary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    เฉ
    -0.06
     /*#__
    -0.06
    Protection
    -0.06
    κό
    -0.06
     unfortunately
    -0.06
     didSelect
    -0.06
    _thresh
    -0.06
     느
    -0.06
    액
    -0.06
    "*
    -0.06
    POSITIVE LOGITS
     Resume
    0.07
    (acc
    0.07
    "title
    0.06
    summary
    0.06
     無
    0.06
     Searches
    0.06
    	glut
    0.06
     comprises
    0.06
    (word
    0.06
     struggles
    0.06
    Act Density 0.001%

    No Known Activations