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

    Neuronpedia

    INDEX
    Explanations

    septic systems

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the word “septic” (including its subparts).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     philosophers
    -0.07
    iye
    -0.07
    .valid
    -0.06
    .integer
    -0.06
    kům
    -0.06
     matchups
    -0.06
     decorated
    -0.06
     Verfügung
    -0.06
     msgs
    -0.06
    iд
    -0.06
    POSITIVE LOGITS
     competent
    0.07
     bookstore
    0.06
     quant
    0.06
    _lex
    0.06
    κι
    0.06
     عق
    0.06
     Ive
    0.06
    ?id
    0.06
     TLabel
    0.06
    har
    0.06
    Act Density 0.003%

    No Known Activations