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

    Neuronpedia

    INDEX
    Explanations

    provides

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fcn
    -0.07
     �
    -0.07
    BuildContext
    -0.07
    <Rigidbody
    -0.06
    泊
    -0.06
    	valid
    -0.06
     TempData
    -0.06
    ığ
    -0.06
     pís
    -0.06
     shelters
    -0.06
    POSITIVE LOGITS
    追加
    0.07
    .scatter
    0.07
    lerde
    0.06
    (e
    0.06
     Adds
    0.06
     consist
    0.06
    554
    0.06
     worldly
    0.06
    providers
    0.06
     wrapper
    0.06
    Act Density 0.046%

    No Known Activations