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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outward
    -0.07
    _half
    -0.07
     Streets
    -0.07
    _every
    -0.07
     classics
    -0.06
    -default
    -0.06
     interacting
    -0.06
     complications
    -0.06
    rade
    -0.06
    instruction
    -0.06
    POSITIVE LOGITS
     \
↵
    0.07
     CLICK
    0.07
     Lindsey
    0.06
     Break
    0.06
     증가
    0.06
    $/)
    0.06
    ัค
    0.06
    ragment
    0.06
     територ
    0.06
     řid
    0.06
    Act Density 0.014%

    No Known Activations