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

    Neuronpedia

    INDEX
    Explanations

    web pages or code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (
    -0.43
    ",
    -0.41
     "
    -0.40
    StackSize
    -0.40
    "
    -0.39
     <<
    -0.39
    .
    -0.38
     at
    -0.37
     for
    -0.37
    ,
    -0.37
    POSITIVE LOGITS
    ^(@)
    0.97
     Normdatei
    0.95
    ValueStyle
    0.89
    ########.
    0.85
     الحره
    0.85
     houſe
    0.84
    styleType
    0.84
     ſtate
    0.84
     transfieras
    0.81
     ſmall
    0.81
    Act Density 0.003%

    No Known Activations