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

    Neuronpedia

    INDEX
    Explanations

    long

    np_max-act · gemini-2.0-flash

    This neuron does not activate on any of the shown tokens—it appears to be effectively “dead” in these contexts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     rallied
    -0.07
     quest
    -0.07
     tùy
    -0.06
    áze
    -0.06
     β
    -0.06
     moins
    -0.06
    _mpi
    -0.06
    制造
    -0.06
     TEXT
    -0.06
     donc
    -0.06
    POSITIVE LOGITS
     advocates
    0.06
    entered
    0.06
    천
    0.06
    .setSelected
    0.06
    _complete
    0.06
     edeb
    0.06
    roach
    0.06
    whether
    0.06
    (attributes
    0.06
    .mouse
    0.06
    Act Density 0.002%

    No Known Activations