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

    Neuronpedia

    INDEX
    Explanations

    memory

    np_max-act · gemini-2.0-flash

    The neuron activates on terms relating to memory and forgetting (e.g., “memory,” “amnesia,” “recall”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    เหน
    -0.06
     عص
    -0.06
     Pompeo
    -0.06
     zak
    -0.06
    807
    -0.06
    NibName
    -0.06
     knots
    -0.06
    raz
    -0.06
     ambitious
    -0.06
     ціл
    -0.06
    POSITIVE LOGITS
     sensation
    0.07
     �
    0.06
     Fedora
    0.06
    _uri
    0.06
     senha
    0.06
     vt
    0.06
     MIDI
    0.06
     shouldn
    0.06
     بازی
    0.06
     splash
    0.06
    Act Density 0.009%

    No Known Activations