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

    Neuronpedia

    INDEX
    Explanations

    fragments and misspellings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     llama
    0.50
     VMware
    0.50
     GitHub
    0.47
     codebase
    0.46
     DNN
    0.46
     mostly
    0.46
     URLs
    0.46
     HH
    0.45
     ৭৭
    0.45
     WebSocket
    0.45
    POSITIVE LOGITS
    Czas
    0.45
    ovjek
    0.44
    Profes
    0.42
    Hlav
    0.41
    idlertid
    0.41
     tzv
    0.40
     সহিত
    0.40
     Utd
    0.40
     Fiziki
    0.39
    ナソニック
    0.38
    Act Density 0.298%

    No Known Activations