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

    Neuronpedia

    INDEX
    Explanations

    probabilistic outcomes or specific scenarios

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     یا
    0.50
     ince
    0.50
     morning
    0.48
     or
    0.47
     that
    0.46
    یم
    0.45
     بین
    0.44
     که
    0.44
     WITH
    0.44
    가
    0.44
    POSITIVE LOGITS
    versammlung
    0.49
     exquis
    0.45
    kä
    0.44
    éraires
    0.44
    tsz
    0.44
    ेशंस
    0.44
     стаўкі
    0.44
    rijf
    0.43
    మణ
    0.43
    VhZ
    0.43
    Act Density 0.001%

    No Known Activations