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

    Neuronpedia

    INDEX
    Explanations

    inject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     доме
    -0.07
    'aut
    -0.07
    �
    -0.06
     holiday
    -0.06
     Identity
    -0.06
    her
    -0.06
     ra
    -0.06
    Week
    -0.06
     mob
    -0.06
     مار
    -0.06
    POSITIVE LOGITS
    :NSUTF
    0.07
     (£
    0.06
    POSE
    0.06
     GLint
    0.06
     quotas
    0.06
    ObjectId
    0.06
     Too
    0.06
     mitig
    0.06
    (prediction
    0.06
    rites
    0.06
    Act Density 0.007%

    No Known Activations