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

    Neuronpedia

    INDEX
    Explanations

    bull fighting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    reter
    0.78
    ли
    0.75
    ikale
    0.74
    член
    0.74
    нення
    0.73
    Inventor
    0.72
    Hep
    0.72
     Oft
    0.72
    1
    0.72
    ngths
    0.71
    POSITIVE LOGITS
     futhi
    1.14
     στο
    1.13
     frescoes
    1.10
     masterpieces
    1.09
     apartments
    1.09
     finca
    1.08
     hamburgers
    1.08
     puppet
    1.07
     fabulous
    1.05
     personas
    1.05
    Act Density 0.001%

    No Known Activations