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

    Neuronpedia

    INDEX
    Explanations

    Option, tweet, Digital, Father

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dür
    0.39
     certe
    0.39
     bremsstrahlung
    0.38
     análise
    0.37
    、《
    0.36
     mails
    0.36
     Dokument
    0.35
     bract
    0.35
     analisi
    0.35
    Spor
    0.35
    POSITIVE LOGITS
    Wow
    0.55
     Wow
    0.51
    wow
    0.44
    thread
    0.40
    BREAK
    0.40
    THREAD
    0.39
    image
    0.38
    Congratulations
    0.38
    Mach
    0.37
    IMAGE
    0.37
    Act Density 0.007%

    No Known Activations