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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تصم
    -0.07
     Regarding
    -0.07
     designed
    -0.07
     Europe
    -0.07
     prices
    -0.07
     Leakage
    -0.07
    童
    -0.07
     CFG
    -0.06
     �
    -0.06
    鉄道
    -0.06
    POSITIVE LOGITS
     soaking
    0.06
     cleanly
    0.06
    fell
    0.06
    imesteps
    0.06
    ither
    0.06
     Maxim
    0.06
    umm
    0.06
     soak
    0.05
    program
    0.05
    Bug
    0.05
    Act Density 0.870%

    No Known Activations