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

    Neuronpedia

    INDEX
    Explanations

    potential

    np_max-act · gemini-2.0-flash

    This neuron is essentially inactive—it does not respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    54
    -0.07
    723
    -0.07
     day
    -0.07
     bye
    -0.07
     Clarke
    -0.06
     made
    -0.06
     Course
    -0.06
     clerk
    -0.06
     works
    -0.06
     Rid
    -0.06
    POSITIVE LOGITS
     potential
    0.16
     Potential
    0.14
    Potential
    0.11
    potential
    0.11
     potentially
    0.10
    潜
    0.10
     potentials
    0.09
     possibility
    0.09
     สถาน
    0.08
     kanıt
    0.08
    Act Density 0.028%

    No Known Activations