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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    maktadır
    -0.06
    Component
    -0.06
    े।
    -0.06
    otyp
    -0.06
    ερο
    -0.06
     geomet
    -0.06
    lder
    -0.06
    ी।
    -0.06
    くれた
    -0.06
    аза
    -0.06
    POSITIVE LOGITS
     №
    0.07
    CALL
    0.06
    Configurer
    0.06
    ='-
    0.06
     thrust
    0.06
     tokens
    0.06
     ValidationResult
    0.05
     actu
    0.05
    иск
    0.05
    viewer
    0.05
    Act Density 0.017%

    No Known Activations