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

    Neuronpedia

    INDEX
    Explanations

    educational institutions and courses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ast
    0.42
     kalp
    0.41
    аст
    0.41
    vole
    0.41
    ས་
    0.39
    Angela
    0.38
    습
    0.38
     retweet
    0.38
     rep
    0.37
    ondale
    0.37
    POSITIVE LOGITS
     Mojo
    0.40
     noqa
    0.38
     المبار
    0.38
     Moo
    0.38
     pedagogy
    0.38
     Browse
    0.37
    CAB
    0.36
     Thermodynamics
    0.36
     Pedagog
    0.36
     сво
    0.36
    Act Density 0.001%

    No Known Activations