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

    Neuronpedia

    INDEX
    Explanations

    like

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (browser
    -0.07
    _arr
    -0.06
     доз
    -0.06
     Boots
    -0.06
    Frozen
    -0.06
     split
    -0.06
    (px
    -0.06
    -0.06
     至
    -0.06
     hits
    -0.05
    POSITIVE LOGITS
     like
    0.09
    -like
    0.07
    Like
    0.07
     LIKE
    0.07
    �
    0.07
    LIKE
    0.07
    ến
    0.07
    ــــ
    0.07
    리는
    0.07
     Like
    0.06
    Act Density 0.027%

    No Known Activations