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

    Neuronpedia

    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (internal
    -0.07
    _INS
    -0.07
    ，请
    -0.06
    .Orientation
    -0.06
     upbeat
    -0.06
    θ
    -0.06
    _irq
    -0.06
    они
    -0.06
    -HT
    -0.06
     BIO
    -0.06
    POSITIVE LOGITS
     that
    0.09
    	that
    0.07
    that
    0.07
    INGLE
    0.07
     THAT
    0.07
    _yellow
    0.06
     presume
    0.06
     MLB
    0.06
     Needed
    0.06
    Silver
    0.06
    Act Density 0.057%

    No Known Activations