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

    Neuronpedia

    INDEX
    Explanations

    ous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unveiled
    -0.07
     stunt
    -0.07
    цями
    -0.07
    фор
    -0.06
     dět
    -0.06
    Models
    -0.06
    allback
    -0.06
     slogan
    -0.06
    -La
    -0.06
    otr
    -0.06
    POSITIVE LOGITS
     aque
    0.07
     OPEN
    0.07
     COUR
    0.07
     case
    0.06
     affidavit
    0.06
     urine
    0.06
    case
    0.06
    	inline
    0.06
     water
    0.06
    wyn
    0.06
    Act Density 0.004%

    No Known Activations