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

    Neuronpedia

    INDEX
    Explanations

    .txt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embedding
    -0.07
     coupling
    -0.07
     attacks
    -0.07
    _JO
    -0.07
    (),"
    -0.06
    ):
↵
    -0.06
     ال
    -0.06
     symmetry
    -0.06
     '-',
    -0.06
    .Param
    -0.06
    POSITIVE LOGITS
    affiliate
    0.07
    -demand
    0.07
    inished
    0.06
     pochop
    0.06
    aktiv
    0.06
     bà
    0.06
    partial
    0.06
     muh
    0.06
    คโน
    0.06
     tapered
    0.06
    Act Density 0.001%

    No Known Activations