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

    Neuronpedia

    INDEX
    Explanations

    ==

    np_max-act · gemini-2.0-flash

    This neuron never activates on any token, i.e. it’s effectively “dead” and doesn’t detect any pattern.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     공개
    -0.07
    	gbc
    -0.06
     generalized
    -0.06
     toItem
    -0.06
    aines
    -0.06
    REATED
    -0.06
     Ок
    -0.06
    xee
    -0.06
     aluno
    -0.06
     rượu
    -0.06
    POSITIVE LOGITS
     unfore
    0.06
    .rules
    0.06
    .dst
    0.06
     цін
    0.06
    Bet
    0.06
    Cómo
    0.06
    dest
    0.06
     jobId
    0.06
    ounge
    0.06
    dou
    0.06
    Act Density 0.016%

    No Known Activations