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

    Neuronpedia

    INDEX
    Explanations

    non-English characters mixed with code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Keine
    0.81
     Pong
    0.67
     Pati
    0.65
     Mai
    0.64
     Monster
    0.64
     Electromagnetic
    0.63
     Connectivity
    0.63
     Sena
    0.62
     पैसे
    0.62
     Eller
    0.62
    POSITIVE LOGITS
    executions
    0.78
    zeniach
    0.78
     tham
    0.74
    formats
    0.74
    orbid
    0.74
     sommige
    0.72
    leduj
    0.68
    artifact
    0.67
    suffixes
    0.67
    interval
    0.66
    Act Density 0.036%

    No Known Activations