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

    Neuronpedia

    INDEX
    Explanations

    imm

    np_max-act · gemini-2.0-flash

    The neuron fires on occurrences of the word “immobile,” i.e. it detects mentions of immobility.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Feng
    -0.07
    提示
    -0.07
     Sug
    -0.07
    cribed
    -0.07
     chalk
    -0.07
     sudo
    -0.07
     cous
    -0.07
     twist
    -0.06
     candid
    -0.06
    Best
    -0.06
    POSITIVE LOGITS
     Imm
    0.10
    Imm
    0.10
     immobil
    0.10
     imm
    0.09
     immersed
    0.08
     IMM
    0.08
     immense
    0.07
    ime
    0.07
    imm
    0.07
    imary
    0.07
    Act Density 0.013%

    No Known Activations