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

    Neuronpedia

    INDEX
    Explanations

    form submission

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jonathan
    -0.08
     GAS
    -0.08
     Jesse
    -0.07
    	Item
    -0.07
     fuel
    -0.07
    炷
    -0.07
    -done
    -0.07
     Bol
    -0.07
     Nash
    -0.07
     occupants
    -0.07
    POSITIVE LOGITS
    ูล
    0.07
     noting
    0.07
    �
    0.06
    claim
    0.06
    峋
    0.06
    Ex
    0.06
    う
    0.06
    .XtraPrinting
    0.06
    .Transparent
    0.06
    ἑ
    0.06
    Act Density 0.025%

    No Known Activations