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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('(
    -0.07
    捷
    -0.07
    低温
    -0.07
    אמר
    -0.06
    佛教
    -0.06
     Marriott
    -0.06
    שותף
    -0.06
    ﱏ
    -0.06
    vendor
    -0.06
    سعادة
    -0.06
    POSITIVE LOGITS
     huh
    0.07
    …the
    0.07
     <$
    0.07
     WHICH
    0.06
     spear
    0.06
    .Room
    0.06
     constructs
    0.06
    eft
    0.06
    leting
    0.06
     Outputs
    0.06
    Act Density 0.006%

    No Known Activations