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

    Neuronpedia

    INDEX
    Explanations

    dry

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onz
    -0.28
    utz
    -0.26
    (option
    -0.26
     somewhere
    -0.26
     STUD
    -0.26
    ade
    -0.26
     scratch
    -0.25
    é«Ń
    -0.25
    ESA
    -0.25
     Puerto
    -0.25
    POSITIVE LOGITS
    -CS
    0.27
     chai
    0.27
    yo
    0.27
    大çļĦ
    0.25
    hythm
    0.24
    æ´Ĺå¹²åĩĢ
    0.24
    faith
    0.24
     related
    0.24
    latin
    0.23
    çļĦè¡£æľį
    0.23
    Act Density 0.004%

    No Known Activations