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

    Neuronpedia

    INDEX
    Explanations

    darkness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >No
    -0.07
    >K
    -0.07
    Voltage
    -0.07
     세
    -0.06
    Philadelphia
    -0.06
    mach
    -0.06
    세요
    -0.06
    ™
    -0.06
     권
    -0.06
    439
    -0.06
    POSITIVE LOGITS
     домашних
    0.06
    Retention
    0.06
    monic
    0.06
    pick
    0.06
     Bans
    0.06
    :inline
    0.06
    pons
    0.06
     ons
    0.06
     hoof
    0.06
     attendance
    0.06
    Act Density 0.064%

    No Known Activations