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

    Neuronpedia

    INDEX
    Explanations

    Code/programming text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     configs
    -0.07
     psychologically
    -0.07
    Protocol
    -0.07
    voir
    -0.07
    ows
    -0.07
    rac
    -0.06
    iren
    -0.06
    —it
    -0.06
     меня
    -0.06
     sensations
    -0.06
    POSITIVE LOGITS
     dishwasher
    0.07
    %</
    0.07
    ,callback
    0.06
    //{↵
    0.06
    -move
    0.06
    していた
    0.06
    グル
    0.06
     -->↵
    0.06
    )();↵
    0.06
     Instant
    0.06
    Act Density 0.017%

    No Known Activations