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

    Neuronpedia

    INDEX
    Explanations

    hardware limitations and specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     пода
    0.71
     магистра
    0.70
     Ing
    0.70
    Terr
    0.70
     Terr
    0.69
     Er
    0.68
     Hunter
    0.67
    эм
    0.66
     Á
    0.63
    threaded
    0.63
    POSITIVE LOGITS
     limitations
    0.84
     entsprechende
    0.79
    constraints
    0.77
     specifics
    0.70
    ៀប
    0.70
    ህል
    0.70
     décrite
    0.69
    SECUR
    0.67
    limits
    0.67
     Limitations
    0.67
    Act Density 0.253%

    No Known Activations