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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (progress
    -0.08
    pytest
    -0.07
    _above
    -0.06
    ために
    -0.06
    olumes
    -0.06
    _handler
    -0.06
    ату
    -0.06
    既然
    -0.06
     pixel
    -0.06
     якій
    -0.06
    POSITIVE LOGITS
     hashmap
    0.07
     ')';↵
    0.07
     Recon
    0.07
     lifting
    0.07
     oğlu
    0.06
    TO
    0.06
    icrobial
    0.06
     HOLD
    0.06
    edic
    0.06
    <KeyValuePair
    0.06
    Act Density 0.296%

    No Known Activations