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

    Neuronpedia

    INDEX
    Explanations

    formal communication templates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subgoal
    0.37
     misinformation
    0.32
     reservoir
    0.32
     otrzym
    0.32
     prestazioni
    0.32
     analogies
    0.31
     arrows
    0.31
     catedral
    0.31
    echolog
    0.31
     dimerization
    0.31
    POSITIVE LOGITS
     持
    0.34
    mtext
    0.33
    ក
    0.32
     Terbaik
    0.32
     لما
    0.32
    ache
    0.31
    Sample
    0.31
     Gone
    0.31
     MonoBehaviour
    0.31
    版本
    0.30
    Act Density 0.008%

    No Known Activations