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

    Neuronpedia

    INDEX
    Explanations

    API related context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sedent
    -0.10
     pathology
    -0.10
     dispens
    -0.09
     dysfunctional
    -0.09
    .branch
    -0.09
     unfortunate
    -0.09
     metaphor
    -0.08
     recuerdos
    -0.08
    ылып
    -0.08
     발견
    -0.08
    POSITIVE LOGITS
    nonce
    0.13
    Nonce
    0.11
     nonce
    0.11
     hashing
    0.10
    csrf
    0.10
     authentication
    0.10
     encryption
    0.10
     encrypt
    0.10
    _nonce
    0.09
     hashlib
    0.09
    Act Density 0.005%

    No Known Activations