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

    Neuronpedia

    INDEX
    Explanations

    Code libraries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Codec
    -0.07
     серед
    -0.07
    ACKET
    -0.07
    об
    -0.07
    icone
    -0.07
     immersed
    -0.06
    Pair
    -0.06
    156
    -0.06
    uir
    -0.06
    acebook
    -0.06
    POSITIVE LOGITS
    .y
    0.07
     motivations
    0.07
    (QL
    0.07
    .counter
    0.06
     YÖ
    0.06
     �
    0.06
    хран
    0.06
    pay
    0.06
     ply
    0.06
    .rm
    0.06
    Act Density 0.000%

    No Known Activations