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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     الدول
    -0.07
     departing
    -0.07
    ’en
    -0.07
     proč
    -0.06
     �
    -0.06
     nowrap
    -0.06
     osobních
    -0.06
     대답
    -0.06
    -store
    -0.06
    ована
    -0.06
    POSITIVE LOGITS
    _nonce
    0.07
    ezier
    0.06
    birthday
    0.06
    ursal
    0.06
    tweets
    0.05
    _PROC
    0.05
     redraw
    0.05
    UIImageView
    0.05
    nite
    0.05
    SetBranchAddress
    0.05
    Act Density 0.008%

    No Known Activations