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

    Neuronpedia

    INDEX
    Explanations

    Des

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     catchy
    -0.07
     cu
    -0.07
    _checks
    -0.07
    Act
    -0.07
     polít
    -0.06
    _guard
    -0.06
    /context
    -0.06
     Fla
    -0.06
    Winner
    -0.06
    .Join
    -0.06
    POSITIVE LOGITS
    ΙΚΗΣ
    0.07
     Des
    0.07
    istica
    0.06
    aterangepicker
    0.06
     ceux
    0.06
    τρ
    0.06
    NGC
    0.06
     عقد
    0.06
    기로
    0.06
    etag
    0.06
    Act Density 0.003%

    No Known Activations