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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lennon
    -0.07
     hesitate
    -0.07
    /pm
    -0.07
     interpret
    -0.06
     also
    -0.06
     Jonathan
    -0.06
    ops
    -0.06
    يلم
    -0.06
    icon
    -0.06
    =my
    -0.06
    POSITIVE LOGITS
     superheroes
    0.07
     Throne
    0.06
     gsi
    0.06
     Ord
    0.06
    _conf
    0.06
     Stalin
    0.06
    _categories
    0.06
    _goal
    0.06
     ГО
    0.06
     револю
    0.06
    Act Density 0.185%

    No Known Activations