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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     familiarity
    -0.07
    _REUSE
    -0.07
    }));↵
    -0.06
    })↵
    -0.06
    柳
    -0.06
     pageInfo
    -0.06
    =""↵
    -0.06
     //!<
    -0.06
    &&
    -0.06
    crear
    -0.06
    POSITIVE LOGITS
     geometric
    0.06
     reductions
    0.06
     garage
    0.06
     puzzles
    0.06
    levation
    0.06
    rock
    0.06
    oplevel
    0.06
    STER
    0.06
    Contrib
    0.06
    Enemy
    0.06
    Act Density 0.035%

    No Known Activations