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

    Neuronpedia

    INDEX
    Explanations

    navigational queries and conversations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺷ
    0.47
     grievous
    0.45
    abilitas
    0.45
    ي
    0.44
    slack
    0.43
    ш
    0.42
    شب
    0.42
    認め
    0.42
    னு
    0.41
     espero
    0.41
    POSITIVE LOGITS
    Conversation
    0.52
     Conversation
    0.51
     Conversations
    0.51
     conversación
    0.50
    Phase
    0.50
    Password
    0.48
    ProgressListener
    0.48
    0.48
    Commission
    0.47
     Commission
    0.47
    Act Density 0.001%

    No Known Activations