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

    Neuronpedia

    INDEX
    Explanations

    following

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     гром
    -0.07
    大全
    -0.06
     Gregg
    -0.06
    效
    -0.06
    .flatMap
    -0.06
    (top
    -0.06
    .toFloat
    -0.06
    \uB
    -0.06
     salario
    -0.06
    ORK
    -0.06
    POSITIVE LOGITS
     forgotten
    0.08
    lagen
    0.08
    cken
    0.07
    ibles
    0.07
     उसस
    0.07
    mn
    0.07
     Directions
    0.07
    ılır
    0.06
     bicycles
    0.06
     Sexe
    0.06
    Act Density 0.019%

    No Known Activations