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

    Neuronpedia

    INDEX
    Explanations

    descriptive elaboration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     உலகின்
    0.37
     (!)
    0.36
     horrible
    0.34
     estas
    0.33
     नावा
    0.33
     mundial
    0.33
     outlaw
    0.32
    !!!!!!!!
    0.32
    !!!!!!
    0.32
     verdens
    0.32
    POSITIVE LOGITS
     достаточно
    0.38
     довольно
    0.38
     досить
    0.34
    有一定的
    0.32
     заинтересо
    0.32
    꽤
    0.32
     поскольку
    0.32
     accountability
    0.31
    BinaryOperation
    0.31
    ትር
    0.31
    Act Density 0.233%

    No Known Activations