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

    Neuronpedia

    INDEX
    Explanations

    error handling and booleans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Huge
    0.46
    oises
    0.44
    চীনের
    0.44
     consolation
    0.44
     stroll
    0.43
     acclaim
    0.43
    लिनी
    0.42
    Colombia
    0.42
    菪
    0.41
    Scores
    0.41
    POSITIVE LOGITS
    ani
    0.47
    انی
    0.46
    ati
    0.44
     seper
    0.43
     speaker
    0.43
     হার
    0.42
     അന
    0.42
    ாது
    0.42
     rebel
    0.42
     政府
    0.41
    Act Density 0.000%

    No Known Activations