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

    Neuronpedia

    INDEX
    Explanations

    V

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     RN
    -0.07
     Txt
    -0.06
    uno
    -0.06
     expos
    -0.06
    .assignment
    -0.06
    Tokenizer
    -0.06
    Built
    -0.06
    snap
    -0.06
    (t
    -0.06
    _upload
    -0.06
    POSITIVE LOGITS
    těl
    0.07
    ِب
    0.06
    κό
    0.06
     парт
    0.06
    egree
    0.06
    �
    0.06
     Draco
    0.06
    ері
    0.06
     Gran
    0.06
     Inspir
    0.06
    Act Density 0.000%

    No Known Activations