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

    Neuronpedia

    INDEX
    Explanations

    fare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     keeper
    -0.07
    ós
    -0.06
    יצב
    -0.06
    母
    -0.06
     caso
    -0.06
     Lindsey
    -0.06
     víde
    -0.06
     asteroid
    -0.06
     Boris
    -0.06
    𬶮
    -0.06
    POSITIVE LOGITS
     INTERRUPTION
    0.08
     wah
    0.07
     couleur
    0.07
    仇
    0.07
     outraged
    0.07
     SKF
    0.07
    (tuple
    0.07
    redients
    0.06
    sut
    0.06
    的内容
    0.06
    Act Density 0.006%

    No Known Activations