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

    Neuronpedia

    INDEX
    Explanations

    purpose or function

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    作为
    0.45
     jako
    0.40
    作為
    0.39
    枃
    0.39
     sebagai
    0.38
    ؔ
    0.37
     énon
    0.36
    חו
    0.34
    продук
    0.34
     ሂደ
    0.34
    POSITIVE LOGITS
     purposes
    0.71
     Purposes
    0.64
     extraordinaire
    0.62
     역할을
    0.52
     substitute
    0.52
     alternativa
    0.51
    alternative
    0.51
     alternative
    0.50
    tool
    0.48
     средство
    0.48
    Act Density 0.050%

    No Known Activations