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

    Neuronpedia

    INDEX
    Explanations

    architecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Already
    -0.07
     Ri
    -0.07
    .Enc
    -0.07
     Pref
    -0.07
    від
    -0.06
     ].
    -0.06
    _preview
    -0.06
     Ş
    -0.06
     فارس
    -0.06
    .fhir
    -0.06
    POSITIVE LOGITS
     wrapper
    0.07
     Quantity
    0.06
     Alias
    0.06
    Prototype
    0.06
     Albums
    0.06
     tactics
    0.06
     sacram
    0.06
    -character
    0.06
    trie
    0.06
    premium
    0.06
    Act Density 0.008%

    No Known Activations