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

    Neuronpedia

    INDEX
    Explanations

    identification and records

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     highlight
    -0.71
     highlights
    -0.66
     supplémentaires
    -0.66
     grounds
    -0.63
     nakalista
    -0.63
    ThroughAttribute
    -0.61
     identifies
    -0.60
    Highlight
    -0.60
     Grounds
    -0.59
    highlights
    -0.59
    POSITIVE LOGITS
    DOCTYPE
    0.68
    </thead>
    0.64
    +:+
    0.57
    ISupport
    0.57
     Emig
    0.57
    ومة
    0.56
     EconPapers
    0.56
    Tazama
    0.54
     emig
    0.54
    #+#
    0.52
    Act Density 0.194%

    No Known Activations