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

    Neuronpedia

    INDEX
    Explanations

    finding something

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ื่
    -0.08
     rud
    -0.08
    ắc
    -0.08
    StreamWriter
    -0.06
    ğ
    -0.06
    cplusplus
    -0.06
    �
    -0.06
     внутр
    -0.06
    	router
    -0.06
    OVID
    -0.06
    POSITIVE LOGITS
    对方
    0.07
     bitch
    0.07
    _ter
    0.07
    [res
    0.07
     Twitch
    0.07
     vrij
    0.06
     trot
    0.06
    (par
    0.06
     Bison
    0.06
     Fort
    0.06
    Act Density 0.115%

    No Known Activations