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

    Neuronpedia

    INDEX
    Explanations

    what kind or type

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     которое
    0.25
     With
    0.25
     If
    0.24
     、
    0.24
     Without
    0.23
     Sum
    0.23
     Your
    0.23
     Any
    0.22
     ,
    0.22
          
    0.22
    POSITIVE LOGITS
     happened
    0.45
     happens
    0.40
     kind
    0.40
     else
    0.39
    soever
    0.37
     sort
    0.34
     kinds
    0.34
    kind
    0.33
     they
    0.29
     constitutes
    0.29
    Act Density 0.070%

    No Known Activations