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

    Neuronpedia

    INDEX
    Explanations

    :\

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sınav
    -0.07
    everyone
    -0.07
    utan
    -0.07
    redit
    -0.07
     Everyone
    -0.06
     taxpayer
    -0.06
     modules
    -0.06
     uniforms
    -0.06
    logs
    -0.06
    favorite
    -0.06
    POSITIVE LOGITS
     eş
    0.08
     Dub
    0.06
     näch
    0.06
     guiActive
    0.06
     보
    0.06
    /tinyos
    0.06
    Mathf
    0.06
    łe
    0.06
    ："
    0.06
    Ь
    0.06
    Act Density 0.004%

    No Known Activations