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

    Neuronpedia

    INDEX
    Explanations

    URLs and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     neurolog
    0.56
     clichés
    0.48
     camaraderie
    0.47
     genre
    0.47
     empathy
    0.46
     bootstrap
    0.46
     virtu
    0.44
     repertoire
    0.44
     murals
    0.44
     clientèle
    0.44
    POSITIVE LOGITS
     hydroxide
    0.63
     chlorides
    0.63
    ocarbon
    0.63
    ohid
    0.62
     hydrogen
    0.61
    Hydrogen
    0.61
    溶液
    0.60
    assium
    0.59
     excreted
    0.59
    水
    0.59
    Act Density 0.051%

    No Known Activations