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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pos
    -0.07
     の
    -0.06
     Blocks
    -0.06
     paralysis
    -0.06
    zes
    -0.06
     tracing
    -0.06
     scan
    -0.06
     ----------------------------------------------------------------------------↵
    -0.06
    ties
    -0.06
     households
    -0.06
    POSITIVE LOGITS
    reatment
    0.06
    inea
    0.06
     Europa
    0.06
    าชน
    0.06
    чої
    0.06
    =:
    0.06
    izzard
    0.06
    ілля
    0.06
     Match
    0.06
    (Bit
    0.06
    Act Density 0.021%

    No Known Activations