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

    Neuronpedia

    INDEX
    Explanations

    the word "weapon"

    oai_token-act-pair · gemini-2.0-flash

    weapon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     je
    -0.62
     to
    -0.60
     so
    -0.57
     are
    -0.57
     an
    -0.56
     a
    -0.54
     in
    -0.52
     at
    -0.52
     van
    -0.51
     démarche
    -0.51
    POSITIVE LOGITS
    ########.
    1.30
     myſelf
    1.23
     تانيه
    1.23
    PerformLayout
    1.19
     متعلقه
    1.16
    ंदीखरीदारी
    1.09
     StringTokenizer
    1.09
    IntoConstraints
    1.08
     >=",
    1.08
     MainAxisSize
    1.07
    Act Density 1.161%

    No Known Activations