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

    Neuronpedia

    INDEX
    Explanations

    outline

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Member
    -0.08
    Javascript
    -0.08
    erialization
    -0.07
    协
    -0.07
    ursor
    -0.07
    (NUM
    -0.07
     sprint
    -0.07
     KeyValuePair
    -0.07
    (Component
    -0.07
    _match
    -0.07
    POSITIVE LOGITS
     были
    0.08
    にくい
    0.07
    ᴰ
    0.07
    -best
    0.07
     done
    0.07
    elles
    0.07
    Qed
    0.07
    きれい
    0.06
     들
    0.06
    ________________________________
    0.06
    Act Density 0.001%

    No Known Activations