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

    Neuronpedia

    INDEX
    Explanations

    you call him

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    те
    1.19
    й
    1.14
    ual
    1.10
    diox
    1.08
     permutations
    1.06
     pondered
    1.06
     divers
    1.04
    否则
    0.99
    多元
    0.96
    ি
    0.95
    POSITIVE LOGITS
     ampliar
    1.34
    maßen
    1.29
    irá
    1.23
     namens
    1.22
    igel
    1.18
    ımda
    1.18
     Girlfriend
    1.16
    ار
    1.16
     Grenze
    1.13
     conoscere
    1.13
    Act Density 0.000%

    No Known Activations