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

    Neuronpedia

    INDEX
    Explanations

    monsters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Chair
    -0.07
     ****
    -0.06
     Poor
    -0.06
    ายใน
    -0.06
    Employees
    -0.06
    >Your
    -0.06
    _robot
    -0.06
    ()));↵↵
    -0.06
    	In
    -0.06
    getStatus
    -0.06
    POSITIVE LOGITS
    áh
    0.07
     profiling
    0.06
    ltre
    0.06
    usunda
    0.06
    чки
    0.06
    łu
    0.06
    callable
    0.06
     dhe
    0.06
     robert
    0.06
     hva
    0.06
    Act Density 0.002%

    No Known Activations