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

    Neuronpedia

    INDEX
    Explanations

    aisle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Disp
    -0.07
     scam
    -0.07
     Inf
    -0.07
     organizers
    -0.07
    Rus
    -0.07
    Out
    -0.07
     mapa
    -0.07
    Stay
    -0.07
     rightly
    -0.06
     legends
    -0.06
    POSITIVE LOGITS
    97
    0.07
    ۰۰
    0.06
     suchen
    0.06
     αυτή
    0.06
    idar
    0.06
    FIRST
    0.06
     altına
    0.06
     ")"↵
    0.06
     ginger
    0.06
     �
    0.05
    Act Density 0.005%

    No Known Activations