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

    Neuronpedia

    INDEX
    Explanations

    asset

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Narrated
    -0.06
    vester
    -0.06
    ñana
    -0.06
    TURE
    -0.06
     supremacist
    -0.06
    ardash
    -0.06
    jury
    -0.06
     DRIVER
    -0.06
    Jet
    -0.06
    ujete
    -0.06
    POSITIVE LOGITS
     Mutex
    0.07
     Lindsey
    0.07
    سة
    0.06
     Arithmetic
    0.06
     Petsc
    0.06
    íl
    0.06
    Color
    0.06
    姫
    0.06
    (ts
    0.06
    [dim
    0.06
    Act Density 0.017%

    No Known Activations