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

    Neuronpedia

    INDEX
    Explanations

    list items or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ide
    0.40
    bars
    0.35
     Krak
    0.35
     rég
    0.34
    زيز
    0.34
    fält
    0.34
    rents
    0.33
    álu
    0.32
    ligare
    0.32
     verses
    0.32
    POSITIVE LOGITS
    ↳
    0.40
     방법
    0.39
     작업을
    0.39
     เพ
    0.39
     具体
    0.39
     작업
    0.38
     использовании
    0.38
     तहत
    0.37
     эл
    0.37
     포
    0.37
    Act Density 0.029%

    No Known Activations