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

    Neuronpedia

    INDEX
    Explanations

    creating, spreading, promoting, exploiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Attempts
    0.41
    行う
    0.37
     사용하는
    0.36
    Attempts
    0.36
    Generating
    0.35
    attempts
    0.35
    converting
    0.34
     alınan
    0.34
     anunciar
    0.33
     attempts
    0.33
    POSITIVE LOGITS
     creation
    0.54
     betterment
    0.50
     promotion
    0.47
    creation
    0.46
     manufacture
    0.44
     simultaneous
    0.43
     detection
    0.42
     development
    0.42
     dissemination
    0.42
     sale
    0.42
    Act Density 0.064%

    No Known Activations