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

    Neuronpedia

    INDEX
    Explanations

    cambridge and bruce names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    っていく
    0.38
    ė
    0.37
    诮
    0.36
    वर्धन
    0.36
    tsconfig
    0.35
    сион
    0.35
     dispar
    0.34
    nb
    0.34
    ланы
    0.34
    0.34
    POSITIVE LOGITS
     Springsteen
    0.46
     চাওয়া
    0.45
     possível
    0.44
     possibles
    0.44
    AKES
    0.43
     knuckles
    0.43
     Ware
    0.43
    可能的
    0.43
     possibile
    0.42
     doctrines
    0.42
    Act Density 0.001%

    No Known Activations