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

    Neuronpedia

    INDEX
    Explanations

    drinking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ฎ
    -0.08
    σκ
    -0.07
     Hük
    -0.07
     budd
    -0.06
    steel
    -0.06
    kubectl
    -0.06
    νομ
    -0.06
     kurulan
    -0.06
    pole
    -0.06
    atri
    -0.06
    POSITIVE LOGITS
    >{↵
    0.07
    /if
    0.06
     Applied
    0.06
    =#{
    0.06
    .quality
    0.06
    /';↵↵
    0.06
     Whole
    0.06
    สะ
    0.06
    Details
    0.06
     Denise
    0.06
    Act Density 0.006%

    No Known Activations