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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =((
    -0.07
    $result
    -0.07
    acity
    -0.06
    -away
    -0.06
    ег
    -0.06
    Timeout
    -0.06
    ulfill
    -0.06
     nozzle
    -0.06
    ork
    -0.06
    jec
    -0.06
    POSITIVE LOGITS
    （笑
    0.08
     Fuß
    0.07
     квітня
    0.06
    uka
    0.06
     APR
    0.06
    opause
    0.06
     slashed
    0.06
    ～↵↵
    0.06
    <usize
    0.06
     START
    0.06
    Act Density 0.029%

    No Known Activations