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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deceased
    -0.07
    =====↵
    -0.07
     itself
    -0.06
    ?↵↵↵
    -0.06
    .Member
    -0.06
     VARIANT
    -0.06
    rowing
    -0.06
     αυ
    -0.06
     themselves
    -0.06
     heroine
    -0.06
    POSITIVE LOGITS
    技
    0.06
     Não
    0.06
     cedar
    0.06
    isease
    0.06
    bow
    0.06
    ublik
    0.06
     strat
    0.06
     rá
    0.06
     glEnable
    0.06
    agal
    0.06
    Act Density 0.048%

    No Known Activations