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

    Neuronpedia

    INDEX
    Explanations

    Plus and minus signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ↵↵↵
    -0.07
    Fall
    -0.07
    طل
    -0.06
     puss
    -0.06
     mouths
    -0.06
    ưở
    -0.06
    áty
    -0.06
    anol
    -0.06
    aleur
    -0.06
    ınd
    -0.06
    POSITIVE LOGITS
     arrangements
    0.06
     DEC
    0.06
     křes
    0.06
     kdyby
    0.06
     travel
    0.05
     wanna
    0.05
    oration
    0.05
    (edit
    0.05
    MethodImpl
    0.05
     Za
    0.05
    Act Density 0.017%

    No Known Activations