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

    Neuronpedia

    INDEX
    Explanations

    compliments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Augusta
    -0.07
    到
    -0.06
    contributors
    -0.06
    Coll
    -0.06
    _Speed
    -0.06
    Projectile
    -0.06
     mente
    -0.05
     git
    -0.05
    	B
    -0.05
    (score
    -0.05
    POSITIVE LOGITS
     BU
    0.07
     optionally
    0.07
    짝
    0.07
    _fragment
    0.07
     glued
    0.07
    ());
    0.07
    identify
    0.06
     sanitize
    0.06
     Tak
    0.06
     deport
    0.06
    Act Density 0.050%

    No Known Activations