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

    Neuronpedia

    INDEX
    Explanations

    banana

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of the word “banana” (including its plural and derivatives).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     UserRole
    -0.08
    �
    -0.07
    760
    -0.07
    第四
    -0.07
    *$
    -0.07
     Pep
    -0.07
    Cadastro
    -0.06
    785
    -0.06
    ４
    -0.06
    四
    -0.06
    POSITIVE LOGITS
     bananas
    0.12
     banana
    0.11
     Banana
    0.10
    ana
    0.07
    line
    0.07
    ange
    0.07
    à
    0.07
    andas
    0.07
    antages
    0.06
    (LayoutInflater
    0.06
    Act Density 0.003%

    No Known Activations