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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :str
    -0.07
     Maggie
    -0.07
    (dummy
    -0.06
     tree
    -0.06
    getText
    -0.06
    urve
    -0.06
    胖
    -0.06
     SUMMARY
    -0.06
    装载
    -0.06
     Still
    -0.06
    POSITIVE LOGITS
     consect
    0.08
     lids
    0.08
    防御
    0.08
    保住
    0.07
    祛
    0.07
     felony
    0.07
    שי
    0.07
    _locator
    0.07
    .AdapterView
    0.07
     consegu
    0.07
    Act Density 0.006%

    No Known Activations