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

    Neuronpedia

    INDEX
    Explanations

    actions and perceptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     peningkatan
    0.45
     very
    0.44
     vrlo
    0.44
     gastronomic
    0.44
     veritable
    0.43
     purely
    0.42
     primary
    0.42
     stylistic
    0.42
     symbiotic
    0.41
     omnichannel
    0.41
    POSITIVE LOGITS
     partake
    0.40
    iyê
    0.39
    চন্দ্রের
    0.39
     retrieve
    0.38
     offend
    0.38
     ConsoleKey
    0.37
     mouve
    0.37
     disobey
    0.37
     మాట్లా
    0.36
     කිය
    0.36
    Act Density 0.078%

    No Known Activations