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

    Neuronpedia

    INDEX
    Explanations

    Wright

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     han
    -0.07
    stackoverflow
    -0.07
     pelo
    -0.06
    semester
    -0.06
     ensuing
    -0.06
     ha
    -0.06
    uka
    -0.06
     korum
    -0.06
     vốn
    -0.06
    ################################################
    -0.06
    POSITIVE LOGITS
     Wright
    0.21
    wright
    0.12
     Dwight
    0.09
    right
    0.08
    (xi
    0.08
    <strong
    0.08
     rights
    0.08
    avier
    0.08
     Xavier
    0.07
     Apt
    0.07
    Act Density 0.001%

    No Known Activations