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

    Neuronpedia

    INDEX
    Explanations

    back

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “back” (often in locational phrases like “back yard,” “back of…”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ebilir
    -0.07
    ค
    -0.07
    204
    -0.07
     א
    -0.06
     IPC
    -0.06
     Wolverine
    -0.06
     GetHashCode
    -0.06
    iştir
    -0.06
     Suicide
    -0.06
    xml
    -0.06
    POSITIVE LOGITS
     roof
    0.06
     front
    0.06
     carro
    0.06
     hw
    0.06
     fron
    0.06
     Fah
    0.06
     back
    0.06
     tip
    0.06
    leader
    0.06
    Tail
    0.06
    Act Density 0.034%

    No Known Activations