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

    Neuronpedia

    INDEX
    Explanations

    start from scratch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vomit
    0.36
    കുന്ന
    0.36
     leverage
    0.35
     foci
    0.35
     voc
    0.34
     focused
    0.34
     seaweed
    0.34
     Jardin
    0.34
     pou
    0.34
     garner
    0.34
    POSITIVE LOGITS
     प्राणियों
    0.42
    Findings
    0.42
     পছ
    0.41
    ibrated
    0.39
    setInput
    0.39
     महाराष्ट
    0.39
    ਵਾਈ
    0.38
     Findings
    0.38
    findings
    0.37
     जीवों
    0.37
    Act Density 0.013%

    No Known Activations