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

    Neuronpedia

    INDEX
    Explanations

    prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    loge
    -0.07
     Code
    -0.07
     Certification
    -0.07
    减
    -0.07
    يديو
    -0.07
    생
    -0.07
    color
    -0.07
     taxation
    -0.07
     Understand
    -0.07
     navigation
    -0.07
    POSITIVE LOGITS
    之一
    0.10
    sas
    0.09
     bied
    0.08
    -mentioned
    0.08
     получится
    0.08
     moisturizing
    0.08
     Pitts
    0.08
    ામાં
    0.08
     juist
    0.08
     .=
    0.08
    Act Density 0.002%

    No Known Activations