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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rock
    -0.08
    marvin
    -0.07
    κας
    -0.07
    まと
    -0.07
     supervise
    -0.06
    _frequency
    -0.06
     BUF
    -0.06
    apiro
    -0.06
    lun
    -0.06
    teen
    -0.06
    POSITIVE LOGITS
     зако
    0.06
     puzzles
    0.06
    'nde
    0.06
     induced
    0.06
     attaching
    0.06
     strs
    0.06
    _style
    0.06
     字
    0.06
    	type
    0.06
    NgModule
    0.06
    Act Density 0.146%

    No Known Activations