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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hosp
    -0.07
    ilebilir
    -0.06
     grat
    -0.06
    λαμβ
    -0.06
    versible
    -0.06
     acompañ
    -0.06
    kö
    -0.06
    -upper
    -0.06
    _ylabel
    -0.06
     сол
    -0.06
    POSITIVE LOGITS
     plus
    0.07
     linked
    0.06
     loaded
    0.06
     Serena
    0.06
    _amount
    0.06
     demand
    0.06
     Doyle
    0.06
    刻
    0.06
    851
    0.06
     functions
    0.06
    Act Density 0.000%

    No Known Activations