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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cater
    -0.07
     ICU
    -0.07
     Marines
    -0.06
     výši
    -0.06
     Choi
    -0.06
    _NUM
    -0.06
     gây
    -0.06
     YT
    -0.06
     partnering
    -0.06
     Carm
    -0.06
    POSITIVE LOGITS
     примен
    0.07
    hur
    0.06
    elidir
    0.06
     //------------------------------------------------
    0.06
     successor
    0.06
     먹
    0.06
    ن
    0.06
    Flag
    0.06
     receive
    0.06
     отправ
    0.06
    Act Density 0.000%

    No Known Activations