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

    Neuronpedia

    INDEX
    Explanations

    plan

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [_
    -0.07
    ('-
    -0.07
     Simpson
    -0.06
    еред
    -0.06
     buckets
    -0.06
     Wright
    -0.06
     Rh
    -0.06
     democratic
    -0.06
     Starbucks
    -0.06
    umper
    -0.06
    POSITIVE LOGITS
     jMenuItem
    0.07
    CustomLabel
    0.07
     know
    0.06
     glfw
    0.06
     정말
    0.06
     plan
    0.06
     plais
    0.06
     italian
    0.06
    MenuBar
    0.06
    compute
    0.06
    Act Density 0.010%

    No Known Activations