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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     declare
    -0.07
     tobacco
    -0.07
     Johan
    -0.06
     lift
    -0.06
    cak
    -0.06
     No
    -0.06
    igslist
    -0.06
    еров
    -0.06
    theless
    -0.06
     boiled
    -0.06
    POSITIVE LOGITS
    _column
    0.06
    _TRIANGLES
    0.06
    (req
    0.06
    SCRIPT
    0.06
     STANDARD
    0.06
    )))↵↵↵
    0.06
    ">
↵
↵
    0.06
    	meta
    0.06
    _MODULE
    0.06
     pussy
    0.05
    Act Density 0.034%

    No Known Activations