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

    Neuronpedia

    INDEX
    Explanations

    This

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Racing
    -0.07
     المك
    -0.07
     那
    -0.06
     doctor
    -0.06
    Ocean
    -0.06
    ittel
    -0.06
     heb
    -0.06
    chool
    -0.06
    계획
    -0.06
    .aws
    -0.06
    POSITIVE LOGITS
     graph
    0.07
    aload
    0.07
     são
    0.07
     seamless
    0.07
    niejs
    0.06
     compass
    0.06
    �
    0.06
    affected
    0.06
    payer
    0.06
    CAD
    0.06
    Act Density 0.050%

    No Known Activations