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

    Neuronpedia

    INDEX
    Explanations

    Academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chy
    -0.07
     Cath
    -0.06
     مناس
    -0.06
     wishes
    -0.06
    匹
    -0.06
     contraseña
    -0.06
     causa
    -0.06
    _food
    -0.06
    ftime
    -0.06
    อลล
    -0.06
    POSITIVE LOGITS
     后
    0.07
    LETTE
    0.07
    .ibatis
    0.06
    rik
    0.06
    875
    0.06
    -disable
    0.06
    having
    0.06
    ingers
    0.06
    berry
    0.06
    however
    0.06
    Act Density 0.250%

    No Known Activations