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

    Neuronpedia

    INDEX
    Explanations

    include

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shapiro
    -0.06
     Fuk
    -0.06
     Rhe
    -0.06
    iew
    -0.06
     Ran
    -0.06
     Summit
    -0.06
     ett
    -0.06
     Miranda
    -0.06
     Jam
    -0.06
     jewellery
    -0.06
    POSITIVE LOGITS
    (end
    0.07
    ondheim
    0.07
     possono
    0.07
    (base
    0.06
    ,LOCATION
    0.06
    (kind
    0.06
     Pikachu
    0.06
    \Bundle
    0.06
    (h
    0.06
     Εν
    0.06
    Act Density 0.030%

    No Known Activations