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

    Neuronpedia

    INDEX
    Explanations

    final answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    buri
    0.45
     Maid
    0.41
    Cor
    0.40
     शै
    0.39
     shelled
    0.39
     bure
    0.38
     bors
    0.38
    シェ
    0.37
     cor
    0.37
    Clo
    0.37
    POSITIVE LOGITS
     Am
    0.36
    Am
    0.36
     Fitch
    0.35
     EAR
    0.35
    イルド
    0.34
    fi
    0.33
    を担当
    0.33
    アリング
    0.33
    för
    0.33
     FV
    0.33
    Act Density 0.010%

    No Known Activations