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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     full
    -0.07
     sample
    -0.07
     coinvol
    -0.07
     istedi
    -0.07
     key
    -0.06
    Pendant
    -0.06
     increase
    -0.06
     podcast
    -0.06
    Pending
    -0.06
    Active
    -0.06
    POSITIVE LOGITS
     remnants
    0.11
     પરથી
    0.11
     ancestor
    0.11
     predecessors
    0.10
     predecessor
    0.10
    _proto
    0.10
     precursor
    0.10
     vidare
    0.10
    માંથી
    0.09
     ancestors
    0.09
    Act Density 0.038%

    No Known Activations