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

    Neuronpedia

    INDEX
    Explanations

    formal/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    WEBPACK
    -0.51
    UserScript
    -0.51
    GIH
    -0.50
     nowhere
    -0.50
    trägen
    -0.47
     EconPapers
    -0.47
    Carriera
    -0.45
     Ceremon
    -0.45
    ContextHolder
    -0.44
    Skocz
    -0.43
    POSITIVE LOGITS
    Портал
    0.63
    werty
    0.59
    ोंने
    0.54
    Ingress
    0.53
     blob
    0.52
    sile
    0.52
     sponge
    0.52
     Wikimedijinoj
    0.51
    verwijspagina
    0.50
    poti
    0.50
    Act Density 0.001%

    No Known Activations