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

    Neuronpedia

    INDEX
    Explanations

    conditionality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nickname
    -0.07
    @if
    -0.07
     frames
    -0.07
     checks
    -0.07
     남
    -0.07
     shows
    -0.06
     rack
    -0.06
    .dt
    -0.06
     pixels
    -0.06
     show
    -0.06
    POSITIVE LOGITS
     انت
    0.07
     Andreas
    0.07
     Naturally
    0.06
     зах
    0.06
    entially
    0.06
     тяж
    0.06
     Titanic
    0.06
    keterangan
    0.06
     appellate
    0.06
     常
    0.06
    Act Density 0.152%

    No Known Activations