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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     minded
    -0.07
    ो,
    -0.07
    ?('
    -0.07
    ΄
    -0.07
     ⟨
    -0.07
    _PHY
    -0.06
    .addAll
    -0.06
     giác
    -0.06
    {return
    -0.06
     Tf
    -0.06
    POSITIVE LOGITS
    YLON
    0.07
     messy
    0.06
     étaient
    0.06
     plut
    0.06
     encuent
    0.06
     Correspond
    0.06
    мож
    0.06
     EU
    0.06
     Riot
    0.05
    logo
    0.05
    Act Density 0.612%

    No Known Activations