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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the substring “hkl” (as in variable or parameter names like H K L or hkl).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.07
     soud
    -0.06
    .getLeft
    -0.06
    ่าท
    -0.06
    fac
    -0.06
    ä
    -0.06
     appar
    -0.06
     ventures
    -0.06
    _CI
    -0.06
    —that
    -0.06
    POSITIVE LOGITS
     Pelosi
    0.07
     ساخته
    0.06
    brew
    0.06
     Dylan
    0.06
    .pub
    0.06
    .alibaba
    0.06
     Wilde
    0.06
    _labels
    0.06
    Putin
    0.06
    quila
    0.06
    Act Density 0.000%

    No Known Activations