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

    Neuronpedia

    INDEX
    Explanations

    S

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rune
    -0.09
     marijuana
    -0.07
     accumulate
    -0.07
    زل
    -0.07
    Atlantic
    -0.07
    enance
    -0.06
    람
    -0.06
    ур
    -0.06
     cultiv
    -0.06
     econom
    -0.06
    POSITIVE LOGITS
     spokesperson
    0.07
     plainly
    0.06
    mnop
    0.06
     nutshell
    0.06
    (sizeof
    0.06
     overridden
    0.06
    .toJSONString
    0.06
    .round
    0.06
    	sound
    0.06
    _context
    0.06
    Act Density 0.003%

    No Known Activations