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

    Neuronpedia

    INDEX
    Explanations

    can

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shadows
    -0.07
     Blind
    -0.07
     shitty
    -0.07
    otyping
    -0.07
     Imperial
    -0.06
     introducing
    -0.06
    unted
    -0.06
     Harold
    -0.06
     Chattanooga
    -0.06
    otype
    -0.06
    POSITIVE LOGITS
    。<
    0.07
     gridColumn
    0.07
    �
    0.06
    lassen
    0.06
     vítěz
    0.06
    BIT
    0.06
     погляд
    0.06
    .basename
    0.06
    θν
    0.06
    MORE
    0.06
    Act Density 0.021%

    No Known Activations