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

    Neuronpedia

    INDEX
    Explanations

    crisis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     closest
    -0.07
     bir
    -0.07
    Ci
    -0.06
     THROUGH
    -0.06
    팽
    -0.06
    _create
    -0.06
    距
    -0.06
     tamp
    -0.06
     위해
    -0.06
    -Y
    -0.06
    POSITIVE LOGITS
     القدس
    0.09
    휑
    0.07
     Steelers
    0.07
    Another
    0.07
    הם
    0.06
    (seconds
    0.06
    (hours
    0.06
    耄
    0.06
    ᛟ
    0.06
    clusão
    0.06
    Act Density 0.123%

    No Known Activations