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

    Neuronpedia

    INDEX
    Explanations

    Scientific journal references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ERICA
    -0.07
    ende
    -0.07
     Protein
    -0.07
     herself
    -0.07
     himself
    -0.07
     tumor
    -0.07
    ادی
    -0.06
    edi
    -0.06
    .ml
    -0.06
    idel
    -0.06
    POSITIVE LOGITS
     Nicholson
    0.07
    ों,
    0.06
    "),"
    0.06
     говорит
    0.06
    "+
    0.06
    ,'
    0.06
     ヴ
    0.06
    ],'
    0.06
     αρι
    0.06
    하세요
    0.06
    Act Density 0.032%

    No Known Activations