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

    Neuronpedia

    INDEX
    Explanations

    needing to do something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    锌
    -0.08
    	response
    -0.08
     hydrogen
    -0.07
     ?>"↵
    -0.07
    ビ
    -0.07
    onces
    -0.07
     ciudad
    -0.07
     Cit
    -0.07
     füh
    -0.07
    اهر
    -0.07
    POSITIVE LOGITS
     parms
    0.08
    🌠
    0.07
    続ける
    0.07
    coration
    0.07
    丝丝
    0.07
    .PER
    0.07
    -over
    0.07
     ses
    0.07
     حال
    0.06
     fred
    0.06
    Act Density 0.019%

    No Known Activations