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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Heroes
    -0.07
    ACHED
    -0.07
    depend
    -0.07
    ems
    -0.06
    eden
    -0.06
     Ο
    -0.06
    -posts
    -0.06
    AK
    -0.06
    commission
    -0.06
     transc
    -0.06
    POSITIVE LOGITS
    ]]);↵
    0.07
    ()]);↵
    0.07
    .strategy
    0.07
     Muscle
    0.07
     松
    0.07
     Evan
    0.07
    .species
    0.06
    [edge
    0.06
    !),
    0.06
     **)
    0.06
    Act Density 0.044%

    No Known Activations