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

    Neuronpedia

    INDEX
    Explanations

    code and equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ois
    -0.07
    �
    -0.07
    UAL
    -0.07
    �
    -0.06
     righteous
    -0.06
    asan
    -0.06
    orris
    -0.06
    -runner
    -0.06
    cısı
    -0.06
     pz
    -0.06
    POSITIVE LOGITS
    lowest
    0.06
    rename
    0.06
     Guidelines
    0.06
     реш
    0.06
    .Logic
    0.06
     flying
    0.06
    )*/↵
    0.06
    лату
    0.06
    Active
    0.06
    larg
    0.06
    Act Density 0.000%

    No Known Activations