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

    Neuronpedia

    INDEX
    Explanations

    technical terms

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     connection
    0.57
    毆
    0.57
    entarios
    0.55
    connection
    0.55
     ಕೂಡ
    0.54
    বরা
    0.54
     zelfs
    0.53
    ंत्री
    0.52
    醜
    0.52
    話
    0.51
    POSITIVE LOGITS
    UserPool
    0.62
    TokenType
    0.61
     TERM
    0.57
     Term
    0.52
     Terminator
    0.52
    素质
    0.52
     vertigo
    0.52
    Term
    0.51
    单词
    0.51
     CrossFit
    0.51
    Act Density 0.000%

    No Known Activations