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

    Neuronpedia

    INDEX
    Explanations

    (req

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nobel
    -0.07
    逮
    -0.07
     Seal
    -0.06
     flash
    -0.06
     הבא
    -0.06
     moll
    -0.06
     Apt
    -0.06
     segundos
    -0.06
    /watch
    -0.06
    .mail
    -0.06
    POSITIVE LOGITS
     Images
    0.08
    营收
    0.07
    }`,↵
    0.07
    ">-->↵
    0.07
    ]';↵
    0.07
     предлагает
    0.07
    }`}↵
    0.07
    _repository
    0.07
    corr
    0.07
     Require
    0.07
    Act Density 0.002%

    No Known Activations