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

    Neuronpedia

    INDEX
    Explanations

    terms related to roads or trails

    oai_token-act-pair · gemini-2.0-flash

    Roads and trails

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lightboxes
    -0.79
    IUrlHelper
    -0.79
     auroit
    -0.77
     ainfi
    -0.77
     pouvoit
    -0.77
     feroit
    -0.76
     RIPRODUZIONE
    -0.75
     Jefus
    -0.73
     kaarangay
    -0.72
     ſever
    -0.72
    POSITIVE LOGITS
     g
    0.56
     p
    0.48
     back
    0.48
     double
    0.47
     d
    0.45
     Jaffe
    0.45
    eleste
    0.45
     Gr
    0.43
     ar
    0.42
     auto
    0.42
    Act Density 1.066%

    No Known Activations