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

    Neuronpedia

    INDEX
    Explanations

    scientific texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Block
    -0.06
    .drawable
    -0.06
     goals
    -0.06
     thou
    -0.06
    _episode
    -0.06
     kterých
    -0.06
    [label
    -0.06
     proud
    -0.06
    	start
    -0.06
    ارس
    -0.06
    POSITIVE LOGITS
     departments
    0.07
    __.
    0.07
     MEMBER
    0.06
    AppBar
    0.06
    /exp
    0.06
    ponge
    0.06
    _orig
    0.06
    ric
    0.06
    §Ã
    0.06
    jet
    0.06
    Act Density 0.173%

    No Known Activations