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

    Neuronpedia

    INDEX
    Explanations

    Negative character traits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     butt
    -0.07
    	error
    -0.07
    ată
    -0.06
     PIL
    -0.06
    รค
    -0.06
     spriteBatch
    -0.06
     experi
    -0.06
     پش
    -0.06
     succes
    -0.06
     barbecue
    -0.06
    POSITIVE LOGITS
    ,System
    0.07
    handled
    0.06
     vợ
    0.06
    atisf
    0.06
    (can
    0.06
    vu
    0.06
    onor
    0.06
    llib
    0.06
    's
    0.06
     advertiser
    0.06
    Act Density 0.066%

    No Known Activations