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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    navigate
    -0.06
     человек
    -0.06
     contemplate
    -0.06
    PLEMENT
    -0.06
    UGHT
    -0.06
     enriched
    -0.06
     considered
    -0.06
    
    -0.06
    references
    -0.06
    updates
    -0.06
    POSITIVE LOGITS
    lâm
    0.07
     job
    0.06
    ávají
    0.06
     раньше
    0.06
    _Runtime
    0.06
    _total
    0.06
     刘
    0.06
     renderItem
    0.06
    ادت
    0.06
    ênh
    0.06
    Act Density 0.004%

    No Known Activations