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

    Neuronpedia

    INDEX
    Explanations

    describing state changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    স্তে
    0.42
    幣
    0.40
    露
    0.38
    ీల
    0.37
    leb
    0.37
    लाइड
    0.36
    ++);
    0.36
    争取
    0.36
    iót
    0.36
    応
    0.35
    POSITIVE LOGITS
     entitlement
    0.41
     MHz
    0.38
     %
    0.38
     mechanism
    0.38
     tratados
    0.38
     nearing
    0.37
     dating
    0.37
     forgiving
    0.36
    closure
    0.36
    furan
    0.36
    Act Density 0.001%

    No Known Activations