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

    Neuronpedia

    INDEX
    Explanations

    by the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    okane
    0.43
     шаблон
    0.38
    goo
    0.38
    aughty
    0.37
    hoo
    0.36
     ironically
    0.36
     практики
    0.36
     practise
    0.36
    ByIndex
    0.36
    dys
    0.35
    POSITIVE LOGITS
     breaching
    0.43
     ਸਮ
    0.42
     outages
    0.40
    Lic
    0.40
     Breach
    0.39
     roughness
    0.38
    Kil
    0.38
     migrating
    0.38
    сун
    0.38
    breaking
    0.38
    Act Density 0.000%

    No Known Activations