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

    Neuronpedia

    INDEX
    Explanations

    online help resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Integrative
    0.48
     integrative
    0.43
     хам
    0.41
    }],
    0.40
    क्लेव
    0.40
    కుల
    0.39
     Integral
    0.39
     Beckman
    0.39
     ديال
    0.39
     popularly
    0.39
    POSITIVE LOGITS
     Civ
    0.43
    जि
    0.42
    Civ
    0.42
    みを
    0.41
    SAFE
    0.40
    ום
    0.39
     мень
    0.38
    civ
    0.37
    undefined
    0.37
     civ
    0.36
    Act Density 0.004%

    No Known Activations