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

    Neuronpedia

    INDEX
    Explanations

    Past tense verbs

    np_max-act · gemini-2.0-flash

    The neuron activates on simple past-tense verb forms (e.g., words ending in “-ed”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     sadece
    -0.07
     которым
    -0.07
    ğimiz
    -0.07
    grades
    -0.06
     owl
    -0.06
     ÜNİVERSİTESİ
    -0.06
    ron
    -0.06
    วาม
    -0.06
    eguard
    -0.06
    placeholder
    -0.06
    POSITIVE LOGITS
     shed
    0.07
     inplace
    0.07
    LocalStorage
    0.06
     residues
    0.06
    銀行
    0.06
     Butt
    0.06
     гип
    0.06
     صنعتی
    0.06
     높
    0.06
    tuğ
    0.06
    Act Density 0.072%

    No Known Activations