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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    僅
    -0.07
     Taş
    -0.06
     recht
    -0.06
     afflicted
    -0.06
    �
    -0.06
     Polo
    -0.06
     disappointed
    -0.06
     Monsanto
    -0.06
    為
    -0.06
     pontos
    -0.06
    POSITIVE LOGITS
     recorder
    0.07
     AuthService
    0.07
    sak
    0.06
    (Token
    0.06
     nevě
    0.06
    	score
    0.06
    fn
    0.06
    .Msg
    0.06
    userid
    0.06
     skb
    0.06
    Act Density 0.020%

    No Known Activations