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

    Neuronpedia

    INDEX
    Explanations

    positive evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seeding
    -0.07
     timeline
    -0.07
    -origin
    -0.07
     notification
    -0.06
    _TEXT
    -0.06
     seeded
    -0.06
     SMA
    -0.06
    Detect
    -0.06
     departments
    -0.06
    LEAR
    -0.06
    POSITIVE LOGITS
    _MOD
    0.07
     LogLevel
    0.06
     остров
    0.06
     ply
    0.06
     olacaktır
    0.06
     Extr
    0.06
     ple
    0.06
    joy
    0.06
     그래
    0.06
     bob
    0.06
    Act Density 0.056%

    No Known Activations