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

    Neuronpedia

    INDEX
    Explanations

    movies and acting

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (grammarAccess
    -0.08
     crane
    -0.06
     Guidance
    -0.06
     Lewis
    -0.06
    _clients
    -0.06
    Dark
    -0.06
     подс
    -0.06
    ，现在
    -0.06
     chk
    -0.06
     Alice
    -0.06
    POSITIVE LOGITS
    -ind
    0.07
     Comprehensive
    0.06
    責
    0.06
     deser
    0.06
     cardio
    0.06
    reach
    0.06
     mue
    0.06
    MON
    0.06
     ranged
    0.06
     AssemblyTitle
    0.06
    Act Density 0.006%

    No Known Activations