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

    Neuronpedia

    INDEX
    Explanations

    technical jargon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     contradictions
    -0.08
    etsk
    -0.07
    utan
    -0.07
    webElementXpaths
    -0.07
     mitochond
    -0.07
    机
    -0.06
    เกษตร
    -0.06
     doporuč
    -0.06
    ulated
    -0.06
     contradictory
    -0.06
    POSITIVE LOGITS
    _solution
    0.07
    _blend
    0.07
    .mesh
    0.07
     vak
    0.07
    Surname
    0.06
     Народ
    0.06
    $results
    0.06
    .dt
    0.06
    .geometry
    0.06
    _encoding
    0.06
    Act Density 0.046%

    No Known Activations