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

    Neuronpedia

    INDEX
    Explanations

    meant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sera
    -0.27
     implication
    -0.26
    _comp
    -0.26
    æĹłåģ¿
    -0.25
    ulary
    -0.25
    assist
    -0.25
     presumably
    -0.25
    æļĹ示
    -0.25
     counterpart
    -0.24
     targets
    -0.24
    POSITIVE LOGITS
    纵åIJij
    0.28
    LAY
    0.26
    owie
    0.25
    å¼Ģåĩº
    0.25
    gage
    0.25
    -peer
    0.24
    å¾®è§Ĥ
    0.23
    plitude
    0.23
    ç»Īç»ĵ
    0.23
    æī¾åĩº
    0.23
    Act Density 0.027%

    No Known Activations