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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entrega
    -0.07
    �
    -0.07
     psi
    -0.06
     viscosity
    -0.06
     Coming
    -0.06
    .Actor
    -0.06
     reforms
    -0.06
    LinearLayout
    -0.06
    ilmektedir
    -0.06
     równ
    -0.06
    POSITIVE LOGITS
    Trim
    0.07
    ر
    0.07
     worth
    0.06
    ату
    0.06
    .Unique
    0.06
    prevent
    0.06
     anyhow
    0.06
    贝
    0.06
     pendant
    0.06
     sure
    0.06
    Act Density 0.001%

    No Known Activations