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

    Neuronpedia

    INDEX
    Explanations

    cat and cats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    괌
    0.43
     patriarchal
    0.39
     dredged
    0.39
     hidrógeno
    0.39
    換え
    0.38
     Participant
    0.38
     dredge
    0.38
     Filipino
    0.38
     پاکستانی
    0.37
     windmill
    0.37
    POSITIVE LOGITS
     feline
    1.82
    猫
    1.81
     cat
    1.74
     cats
    1.66
     猫
    1.63
    貓
    1.55
     kitty
    1.51
     Cats
    1.48
    Cats
    1.48
     kucing
    1.48
    Act Density 0.085%

    No Known Activations