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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    λ
    -0.07
    りと
    -0.06
    collapsed
    -0.06
     Decl
    -0.06
     prest
    -0.06
    ept
    -0.06
    lobal
    -0.06
     colony
    -0.06
     обол
    -0.06
    Mal
    -0.06
    POSITIVE LOGITS
    comes
    0.07
    iving
    0.07
     grinder
    0.07
    (int
    0.06
     дина
    0.06
    .IsSuccess
    0.06
    pletion
    0.06
    ToLower
    0.06
    toThrow
    0.06
    566
    0.06
    Act Density 0.001%

    No Known Activations