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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash

    numbers and their associated calculations or manipulations.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    QPushButton
    -0.07
     actionPerformed
    -0.07
    herit
    -0.07
    Rose
    -0.07
     leftovers
    -0.07
    CLE
    -0.06
    En
    -0.06
    問
    -0.06
    Dom
    -0.06
    EINVAL
    -0.06
    POSITIVE LOGITS
    (panel
    0.06
    workers
    0.06
     scientists
    0.06
    ��
    0.06
    .disc
    0.06
    ll
    0.06
     üst
    0.06
    878
    0.06
    .server
    0.06
    .commands
    0.06
    Act Density 0.001%

    No Known Activations