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

    Neuronpedia

    INDEX
    Explanations

    entity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ธ
    -0.08
     McCain
    -0.07
     glitches
    -0.07
    .Pro
    -0.07
    chem
    -0.06
     zdrav
    -0.06
    τσ
    -0.06
    _IT
    -0.06
     Went
    -0.06
    .unlink
    -0.06
    POSITIVE LOGITS
    〉
    0.07
     århus
    0.06
     CLIIIK
    0.06
     resolving
    0.06
    атков
    0.06
    oples
    0.06
     benöt
    0.06
    Users
    0.06
     담
    0.06
    Pen
    0.05
    Act Density 0.100%

    No Known Activations