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

    Neuronpedia

    INDEX
    Explanations

    several good ways

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stoj
    0.43
     thrown
    0.39
    Structure
    0.38
    发育
    0.38
     Rine
    0.37
    лізації
    0.36
    骠
    0.36
    Chord
    0.36
    Zm
    0.36
    机
    0.36
    POSITIVE LOGITS
     അയ
    0.38
     translated
    0.37
     representado
    0.37
     exponer
    0.36
     Buenas
    0.36
     verificar
    0.36
     translation
    0.35
     لە
    0.35
     प्रतिनिधित्व
    0.35
    translation
    0.35
    Act Density 0.000%

    No Known Activations