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

    Neuronpedia

    INDEX
    Explanations

    nothing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     noir
    -0.07
     Woman
    -0.07
    story
    -0.07
    яб
    -0.07
     Records
    -0.06
     Trans
    -0.06
     wiped
    -0.06
     Του
    -0.06
    ряд
    -0.06
     Skyrim
    -0.06
    POSITIVE LOGITS
    -resistant
    0.08
    xAC
    0.07
    .Dir
    0.07
     başlam
    0.06
     ¦
    0.06
    Brit
    0.06
     hiçbir
    0.06
    erusform
    0.06
     complic
    0.06
     streamed
    0.06
    Act Density 0.036%

    No Known Activations