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

    Neuronpedia

    INDEX
    Explanations

    ambitious strategic futures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    released
    0.56
     Released
    0.50
    turbo
    0.46
     darkness
    0.46
    ről
    0.46
     released
    0.45
    科學
    0.45
    RELEASE
    0.44
    tsy
    0.44
     geschrieben
    0.44
    POSITIVE LOGITS
    Loc
    0.46
    Factors
    0.42
    Sal
    0.40
    काल
    0.40
     factors
    0.39
    Philadelphia
    0.39
     সমৃদ্ধ
    0.38
    Matrices
    0.38
     Greenwich
    0.38
     SUBSTIT
    0.38
    Act Density 0.001%

    No Known Activations