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

    Neuronpedia

    INDEX
    Explanations

    had

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.69
    bootstrapcdn
    -0.66
     تضيفلها
    -0.65
    posedge
    -0.64
    Abitanti
    -0.64
    Jeografia
    -0.60
     its
    -0.56
    WriteTagHelper
    -0.56
    prefixer
    -0.56
    nologue
    -0.54
    POSITIVE LOGITS
     Their
    0.85
    Their
    0.81
     their
    0.75
    selves
    0.73
     lives
    0.73
    their
    0.73
     THEIR
    0.68
     faces
    0.65
     minds
    0.64
     yourselves
    0.64
    Act Density 1.475%

    No Known Activations