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

    Neuronpedia

    INDEX
    Explanations

    HIV

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Hal
    -0.08
    (AL
    -0.07
     정도
    -0.07
     Если
    -0.07
     znám
    -0.07
     JOIN
    -0.07
     verbs
    -0.07
    expo
    -0.07
     undecided
    -0.06
     mercado
    -0.06
    POSITIVE LOGITS
     polym
    0.06
    :url
    0.06
     дра
    0.05
    pins
    0.05
    .house
    0.05
    Collider
    0.05
     deter
    0.05
    었다
    0.05
     scour
    0.05
    .s
    0.05
    Act Density 0.011%

    No Known Activations