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
     une
    -0.07
    .pre
    -0.06
     blaming
    -0.06
     Ut
    -0.06
     cinematic
    -0.06
     mars
    -0.06
    Rew
    -0.06
     hadde
    -0.06
    STRU
    -0.06
     queda
    -0.06
    POSITIVE LOGITS
     nicer
    0.08
    216
    0.07
     freeing
    0.07
    tadır
    0.06
    ,j
    0.06
    _offer
    0.06
     Genç
    0.06
     Newly
    0.06
    profil
    0.06
     fringe
    0.06
    Act Density 0.001%

    No Known Activations