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

    Neuronpedia

    INDEX
    Explanations

    loop

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cecil
    -0.07
     nestled
    -0.06
     ged
    -0.06
    icens
    -0.06
    atura
    -0.06
    odka
    -0.06
    fik
    -0.06
    ilia
    -0.06
    stral
    -0.06
    endi
    -0.06
    POSITIVE LOGITS
     loop
    0.13
    _loop
    0.13
     Loop
    0.11
    loop
    0.11
    Loop
    0.11
    _LOOP
    0.09
    (Op
    0.09
     looping
    0.09
    LOOP
    0.09
     LOOP
    0.09
    Act Density 0.013%

    No Known Activations