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

    Neuronpedia

    INDEX
    Explanations

    Fashion industry sentences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    丸
    0.54
    Akt
    0.51
    áž
    0.51
    okus
    0.51
    ﷽
    0.50
    <i>
    0.48
    Ein
    0.47
    Ang
    0.45
    hal
    0.45
    Surname
    0.45
    POSITIVE LOGITS
     been
    0.61
    ׃
    0.59
     সঙ্গে
    0.56
     で
    0.55
     을
    0.55
     ذریعے
    0.55
     에서
    0.54
     साथ
    0.53
     는
    0.53
     गर्नुहोस्
    0.52
    Act Density 0.009%

    No Known Activations