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

    Neuronpedia

    INDEX
    Explanations

    cats and felines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     എന്നാല്‍
    0.53
    उचर
    0.53
    7
    0.53
     मगर
    0.51
    नात्मक
    0.50
     dredging
    0.50
    🛖
    0.50
    UNT
    0.50
    स्परिक
    0.49
     म्हणजे
    0.49
    POSITIVE LOGITS
     cats
    0.95
     feline
    0.88
     kittens
    0.87
    🐱
    0.84
     kucing
    0.78
    猫
    0.75
     puppies
    0.73
     tabby
    0.73
     Cats
    0.72
     반려동
    0.71
    Act Density 0.116%

    No Known Activations