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

    Neuronpedia

    INDEX
    Explanations

    N

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defe
    -0.07
     oprav
    -0.06
     yetiş
    -0.06
    ічні
    -0.06
    (Build
    -0.06
     �
    -0.06
     znam
    -0.06
     }),↵↵
    -0.06
    essage
    -0.06
    lush
    -0.06
    POSITIVE LOGITS
     fingertips
    0.07
     dates
    0.07
    IGO
    0.06
     sentir
    0.06
     muse
    0.06
    Gradient
    0.06
     pres
    0.06
     cuff
    0.06
    wed
    0.06
    _PROM
    0.06
    Act Density 0.000%

    No Known Activations