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

    Neuronpedia

    INDEX
    Explanations

    dates and time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Art
    -0.07
     있었
    -0.07
     WW
    -0.07
     Art
    -0.07
    _edge
    -0.06
     former
    -0.06
    °N
    -0.06
     dar
    -0.06
     dass
    -0.06
    ]',
    -0.06
    POSITIVE LOGITS
     [+
    0.07
     sı
    0.06
     splits
    0.06
    .pickle
    0.06
    (valor
    0.06
     affirmative
    0.06
    τσι
    0.06
    865
    0.06
     hızla
    0.06
    ！');↵
    0.06
    Act Density 0.035%

    No Known Activations