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

    Neuronpedia

    INDEX
    Explanations

    speech following colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    жде
    0.43
    hydration
    0.40
     vuole
    0.38
    */}
    0.37
    ],[
    0.36
     অভাবে
    0.36
    Ṕ
    0.36
    Jim
    0.36
    ه
    0.35
     Jim
    0.35
    POSITIVE LOGITS
     ettha
    0.46
    ത്തിയാ
    0.41
    𝓊
    0.40
     konflikt
    0.38
    uta
    0.38
     conflic
    0.38
    ulik
    0.38
     konflik
    0.37
     periodista
    0.37
     conflicts
    0.37
    Act Density 0.000%

    No Known Activations