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

    Neuronpedia

    INDEX
    Explanations

    interaction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Board
    -0.07
     poetic
    -0.06
     Vinci
    -0.06
     '}
    -0.06
    国
    -0.06
     understandable
    -0.06
    ическое
    -0.06
     Thi
    -0.06
    ุดท
    -0.06
    ації
    -0.06
    POSITIVE LOGITS
    datatype
    0.07
    -native
    0.07
    ài
    0.06
     csr
    0.06
     graceful
    0.06
    shiv
    0.06
    石
    0.06
    στή
    0.06
     encounter
    0.06
     chod
    0.06
    Act Density 0.041%

    No Known Activations