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

    Neuronpedia

    INDEX
    Explanations

    chemicals

    np_max-act · gemini-2.0-flash

    The neuron activates on chemical compound abbreviations or shorthand names (i.e. uppercase letter sequences denoting specific chemicals).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .pipe
    -0.07
     ISSUE
    -0.06
    Founded
    -0.06
    ept
    -0.06
     назива
    -0.06
    JNI
    -0.06
    €€€€
    -0.06
     cloudy
    -0.06
    Matchers
    -0.06
     MutableList
    -0.06
    POSITIVE LOGITS
    (add
    0.07
     진
    0.07
    uyển
    0.07
    حص
    0.06
    롱
    0.06
     打
    0.06
    loom
    0.06
    zend
    0.06
    Segment
    0.06
     extra
    0.06
    Act Density 0.021%

    No Known Activations