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

    Neuronpedia

    INDEX
    Explanations

    bor

    np_max-act · gemini-2.0-flash

    The neuron activates on the “abor” fragment in boron-containing chemical names (e.g. in “dioxaborolane”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     suis
    -0.08
    ��
    -0.07
    fld
    -0.07
    iare
    -0.07
     každý
    -0.07
     muss
    -0.07
    empo
    -0.07
    Parents
    -0.07
    oir
    -0.06
     tarih
    -0.06
    POSITIVE LOGITS
    ＼＼
    0.06
    (username
    0.06
    upos
    0.06
     اصفه
    0.06
    وذ
    0.06
    @Spring
    0.06
     Borg
    0.06
     @"
    0.06
     Pacers
    0.06
     elimination
    0.06
    Act Density 0.004%

    No Known Activations