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

    Neuronpedia

    INDEX
    Explanations

    words related to mystery and intrigue

    oai_token-act-pair · gemini-2.0-flash

    Secrets and intrigue

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.66
    OGND
    -0.59
     pamamagitan
    -0.56
     retenir
    -0.54
     naturels
    -0.52
    WTA
    -0.51
    хіво
    -0.50
     mío
    -0.50
     naturelle
    -0.50
     statunit
    -0.49
    POSITIVE LOGITS
    !*\
    0.59
     متعلقه
    0.54
     propOrder
    0.54
    AddHtmlAttribute
    0.52
    signable
    0.52
    velocityY
    0.52
    getColumnIndex
    0.51
     secret
    0.49
    omock
    0.49
    原始内容存档
    0.49
    Act Density 2.649%

    No Known Activations