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

    Neuronpedia

    INDEX
    Explanations

    dog breeds and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Validation
    0.50
     validation
    0.48
     val
    0.47
     BLE
    0.47
    貓
    0.47
     Validation
    0.46
    BLE
    0.46
    猫
    0.46
    CAT
    0.45
    cats
    0.45
    POSITIVE LOGITS
     Mong
    0.41
    锒
    0.39
    uidas
    0.38
     Kinetic
    0.38
    aniya
    0.37
     প্রবৃত্ত
    0.36
     pud
    0.36
     electrostatic
    0.36
     laborum
    0.35
     Embar
    0.35
    Act Density 0.111%

    No Known Activations