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

    Neuronpedia

    INDEX
    Explanations

    Questions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     learns
    -0.07
     learn
    -0.07
     determine
    -0.07
    /interface
    -0.07
    ervention
    -0.07
     useRouter
    -0.06
     nghe
    -0.06
    LOSS
    -0.06
     metodo
    -0.06
     SUPPORT
    -0.06
    POSITIVE LOGITS
    .then
    0.07
    -var
    0.06
    вад
    0.06
    optimize
    0.06
    *',
    0.06
    0.06
     authenticated
    0.06
    holders
    0.06
     intentions
    0.06
     locals
    0.06
    Act Density 0.038%

    No Known Activations