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

    Neuronpedia

    INDEX
    Explanations

    code, Haskell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    台
    -0.07
    							↵
    -0.07
    ordum
    -0.06
    ектора
    -0.06
     mating
    -0.06
    .Resolve
    -0.06
     ctl
    -0.06
    .TRA
    -0.06
    `${
    -0.06
    POSITIVE LOGITS
    (spell
    0.06
    基于
    0.06
     реш
    0.06
    Subscribe
    0.06
     “
    0.06
    JSONException
    0.06
     velmi
    0.06
    nehmer
    0.06
    برد
    0.06
     pochop
    0.06
    Act Density 0.043%

    No Known Activations