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

    Neuronpedia

    INDEX
    Explanations

    bits

    np_max-act · gemini-2.0-flash

    This neuron never reliably activates on any content – it doesn’t detect any meaningful pattern (i.e. it’s effectively inactive).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    부분
    -0.07
     Salon
    -0.06
    加工
    -0.06
    Amb
    -0.06
     Dob
    -0.06
    .expand
    -0.06
     impatient
    -0.06
    umbn
    -0.06
     Dustin
    -0.06
     shirt
    -0.06
    POSITIVE LOGITS
     осві
    0.07
    .setState
    0.06
    entlich
    0.06
    challenge
    0.06
    Cfg
    0.06
    vido
    0.06
     Oval
    0.06
     $_
    0.06
     wah
    0.06
    RID
    0.06
    Act Density 0.008%

    No Known Activations