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

    Neuronpedia

    INDEX
    Explanations

    avoiding direct answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    println
    -0.07
    urile
    -0.07
     продаж
    -0.06
     Bark
    -0.06
    ιχ
    -0.06
    roids
    -0.06
     стены
    -0.06
     por
    -0.06
     Rolled
    -0.06
     stere
    -0.06
    POSITIVE LOGITS
     muschi
    0.07
     neatly
    0.06
    construct
    0.06
     dataSnapshot
    0.06
    abi
    0.06
    apiKey
    0.06
    Water
    0.06
    .Cell
    0.06
     amended
    0.06
    養
    0.06
    Act Density 0.009%

    No Known Activations