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

    Neuronpedia

    INDEX
    Explanations

    describing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    或者
    1.35
     或者
    1.35
     또는
    1.32
     或
    1.28
    或
    1.27
     அல்லது
    1.27
     alebo
    1.27
     или
    1.24
    又は
    1.23
     یا
    1.22
    POSITIVE LOGITS
     очередной
    0.75
     his
    0.75
     another
    0.72
     the
    0.67
     minuscule
    0.67
     очеред
    0.67
     Another
    0.67
     defunct
    0.66
     indistinct
    0.63
     Suddenly
    0.61
    Act Density 0.109%

    No Known Activations