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

    Neuronpedia

    INDEX
    Explanations

    score

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nexus
    -0.07
    ChildIndex
    -0.07
     Nexus
    -0.07
    Wat
    -0.07
     Dart
    -0.07
    142
    -0.07
    Nation
    -0.07
    ellschaft
    -0.06
     الانت
    -0.06
    /global
    -0.06
    POSITIVE LOGITS
     Score
    0.14
     scores
    0.13
     score
    0.13
     Scores
    0.12
     SCORE
    0.11
    score
    0.11
     scored
    0.10
    Score
    0.10
     Scor
    0.10
     scor
    0.10
    Act Density 0.019%

    No Known Activations