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

    Neuronpedia

    INDEX
    Explanations

    break down explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     flog
    0.51
    :
    0.51
    ፈለ
    0.50
     уви
    0.49
     cortar
    0.49
     see
    0.47
     bonito
    0.47
     kör
    0.46
     pede
    0.46
     bebas
    0.46
    POSITIVE LOGITS
    achel
    0.54
    cpp
    0.50
    impero
    0.49
    versa
    0.48
     aspirants
    0.48
    demo
    0.47
    nomes
    0.47
     Throughout
    0.47
     ലേഖ
    0.47
    exceptions
    0.46
    Act Density 0.000%

    No Known Activations