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

    Neuronpedia

    INDEX
    Explanations

    connector words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lena
    -0.07
    Face
    -0.07
    Evidence
    -0.07
     fout
    -0.06
     PREFIX
    -0.06
    ここ
    -0.06
     Paths
    -0.06
    _UNDEFINED
    -0.06
    _TREE
    -0.06
     lyr
    -0.06
    POSITIVE LOGITS
     dataSnapshot
    0.07
    xAA
    0.07
    (UnmanagedType
    0.07
     Ballard
    0.06
     Coconut
    0.06
     occasional
    0.06
    dimension
    0.06
    EST
    0.06
    .UnitTesting
    0.06
    외
    0.06
    Act Density 0.308%

    No Known Activations