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

    Neuronpedia

    INDEX
    Explanations

    language and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    2
    0.58
    0
    0.46
     Hals
    0.45
     Förder
    0.44
     Home
    0.43
     Griff
    0.43
    ract
    0.42
     Botan
    0.42
     Ambul
    0.42
     Kenn
    0.42
    POSITIVE LOGITS
     megawatts
    0.53
     neutrinos
    0.52
     degassing
    0.51
    Კ
    0.51
     personas
    0.49
    comparing
    0.49
     ပါ
    0.49
     pulsation
    0.49
    languages
    0.49
     kilograms
    0.49
    Act Density 0.000%

    No Known Activations