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

    Neuronpedia

    INDEX
    Explanations

    Family narratives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    plugins
    -0.09
     Challenge
    -0.08
     Monday
    -0.08
    Monday
    -0.08
    Challenge
    -0.08
     Friday
    -0.08
    Friday
    -0.08
     challenge
    -0.08
     hour
    -0.07
    Tuesday
    -0.07
    POSITIVE LOGITS
     לאורך
    0.14
    生命周期
    0.13
     lifelong
    0.13
    Lifecycle
    0.13
     gedurende
    0.13
     lifecycle
    0.13
     生命周期
    0.12
     timeline
    0.12
    Timeline
    0.12
     sepanjang
    0.12
    Act Density 0.065%

    No Known Activations