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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash

    This neuron detects when the user asks if something is required or necessary (e.g., “Do I need …?”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     GetString
    -0.07
    ы
    -0.07
     вив
    -0.06
    ětš
    -0.06
    ska
    -0.06
     Ways
    -0.06
     salv
    -0.06
    Assets
    -0.06
     unhappy
    -0.06
    ƒ
    -0.06
    POSITIVE LOGITS
    mutable
    0.06
     بند
    0.06
    acus
    0.06
     decorative
    0.06
    ,$_
    0.06
    чів
    0.06
    Updating
    0.06
    اپ
    0.06
    babel
    0.06
     важно
    0.06
    Act Density 0.011%

    No Known Activations