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

    Neuronpedia

    INDEX
    Explanations

    crust

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the substring “crust” (e.g. in “crust,” “crustacean,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ange
    -0.07
     debe
    -0.07
    _sep
    -0.07
    _velocity
    -0.07
     došlo
    -0.07
     распростран
    -0.07
    entre
    -0.07
    iên
    -0.07
     Gale
    -0.07
     imshow
    -0.06
    POSITIVE LOGITS
     crust
    0.11
     hull
    0.10
     Hull
    0.09
     skull
    0.08
     Skull
    0.08
    اس
    0.07
     hus
    0.07
    Skin
    0.07
     casing
    0.07
     cartridge
    0.06
    Act Density 0.006%

    No Known Activations