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

    Neuronpedia

    INDEX
    Explanations

    Expressing possibility/solutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utation
    -0.07
     synonym
    -0.06
    -track
    -0.06
    _OK
    -0.06
     suppressed
    -0.06
    oker
    -0.06
    kor
    -0.06
     sky
    -0.06
    Shows
    -0.06
     fists
    -0.06
    POSITIVE LOGITS
     #[
    0.07
     побед
    0.06
     政
    0.06
    :',↵
    0.06
    Dem
    0.06
    _hdl
    0.06
    ระบ
    0.06
     TIMEOUT
    0.06
    licants
    0.06
    �
    0.06
    Act Density 0.035%

    No Known Activations