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

    Neuronpedia

    INDEX
    Explanations

    age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hack
    -0.07
    attached
    -0.07
    ducer
    -0.07
     praise
    -0.06
     '';
↵
    -0.06
    irim
    -0.06
     creds
    -0.06
    arrera
    -0.06
    ۱۹۹
    -0.06
     heroic
    -0.06
    POSITIVE LOGITS
     pers
    0.07
    |↵↵
    0.07
    pora
    0.07
     ortaya
    0.06
    ****************************************************************
    0.06
     anesthesia
    0.06
    .Job
    0.06
    URATION
    0.06
    引
    0.06
     引
    0.06
    Act Density 0.002%

    No Known Activations