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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ToFit
    -0.07
     discounted
    -0.07
     GW
    -0.06
     smarter
    -0.06
     PM
    -0.06
    gado
    -0.06
     Theme
    -0.06
     Crack
    -0.06
     Defendants
    -0.06
    }},↵
    -0.06
    POSITIVE LOGITS
     vyk
    0.07
    ervoir
    0.07
     působ
    0.06
     pigment
    0.06
    씨
    0.06
     různé
    0.06
     Salt
    0.06
    	URL
    0.06
     Marl
    0.06
     Buff
    0.06
    Act Density 0.047%

    No Known Activations