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

    Neuronpedia

    INDEX
    Explanations

    specifying attributes of terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    чена
    0.50
    jetas
    0.48
     აღ
    0.47
     அட்ட
    0.46
    raid
    0.46
     случаях
    0.44
     année
    0.43
     সুখী
    0.42
    ক
    0.42
    atgu
    0.42
    POSITIVE LOGITS
    grund
    0.54
    OUS
    0.44
    暖
    0.44
     maju
    0.44
     cok
    0.43
     Scorpion
    0.43
    彆
    0.43
    かと
    0.43
     warming
    0.42
     arti
    0.42
    Act Density 0.000%

    No Known Activations