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

    Neuronpedia

    INDEX
    Explanations

    record

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sat
    -0.07
    whether
    -0.07
    Gs
    -0.07
     Stories
    -0.06
    Co
    -0.06
    <s
    -0.06
     whether
    -0.06
     wondering
    -0.06
    泰
    -0.06
    proper
    -0.06
    POSITIVE LOGITS
     itk
    0.08
    ्रण
    0.07
    enské
    0.07
    ká
    0.06
     threadIdx
    0.06
    lý
    0.06
     plav
    0.06
    ký
    0.06
     memnun
    0.06
     Operational
    0.06
    Act Density 0.002%

    No Known Activations