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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Event
    -0.07
     Caps
    -0.06
    ická
    -0.06
    cams
    -0.06
     EntityType
    -0.06
     biodiversity
    -0.06
     خی
    -0.06
     reap
    -0.06
     ハ
    -0.06
     fucked
    -0.06
    POSITIVE LOGITS
    cooked
    0.07
     impeachment
    0.07
    ,start
    0.07
    Start
    0.06
    .stdout
    0.06
    ình
    0.06
     помогает
    0.06
    .Red
    0.06
     tracing
    0.06
     foreign
    0.06
    Act Density 0.025%

    No Known Activations