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

    Neuronpedia

    INDEX
    Explanations

    fighting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    onym
    -0.07
     pale
    -0.07
     počet
    -0.07
     лучше
    -0.07
     quien
    -0.07
    就算
    -0.07
     начина
    -0.07
     },
    -0.07
     ssize
    -0.07
    ая
    -0.07
    POSITIVE LOGITS
     persever
    0.08
     analys
    0.07
     enumer
    0.07
    _SCHED
    0.07
    Typ
    0.07
     discrim
    0.07
     inhib
    0.07
    �
    0.07
    -cut
    0.07
     Yield
    0.07
    Act Density 0.451%

    No Known Activations