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

    Neuronpedia

    INDEX
    Explanations

    market reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atypes
    -0.07
    ball
    -0.06
     Accuracy
    -0.06
     вра
    -0.06
     ΕΛ
    -0.06
     khá
    -0.06
    (Math
    -0.06
    ोश
    -0.06
    (box
    -0.06
    .adv
    -0.06
    POSITIVE LOGITS
    singular
    0.07
    titre
    0.07
     příležit
    0.07
     asker
    0.07
     tudo
    0.06
     metallic
    0.06
     prosec
    0.06
     그의
    0.06
     impactful
    0.06
     attended
    0.06
    Act Density 0.004%

    No Known Activations