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

    Neuronpedia

    INDEX
    Explanations

    Philosophical/Academic discussions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     huma
    -0.08
     Nicola
    -0.08
     Miranda
    -0.08
    yttä
    -0.07
     fə
    -0.07
     tuk
    -0.07
     indi
    -0.07
    ℃↵
    -0.07
     있음
    -0.07
     þe
    -0.07
    POSITIVE LOGITS
     implications
    0.12
     standpoint
    0.10
    来看
    0.08
     aspecto
    0.08
     aspects
    0.08
     repercussions
    0.08
     considerations
    0.07
     ramifications
    0.07
    Imp
    0.07
     perspective
    0.07
    Act Density 0.140%

    No Known Activations