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

    Neuronpedia

    INDEX
    Explanations

    Jacob

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ningún
    -0.08
     느
    -0.08
    昃
    -0.08
    重温
    -0.07
    .opens
    -0.07
    ----------------------------------------------------------------------↵
    -0.07
    -port
    -0.07
    上の
    -0.07
    にお
    -0.07
     şü
    -0.07
    POSITIVE LOGITS
     Jacob
    0.10
    Jacob
    0.08
     Jak
    0.07
     Yak
    0.07
     Carolina
    0.07
     Cowboys
    0.07
     multiply
    0.06
     honey
    0.06
    .S
    0.06
    摄入
    0.06
    Act Density 0.007%

    No Known Activations