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

    Neuronpedia

    INDEX
    Explanations

    actions or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     miles
    0.40
     mile
    0.40
     tastes
    0.39
     biom
    0.37
     consommateurs
    0.36
     menjadi
    0.36
     firmly
    0.36
    ะไร
    0.36
     mensen
    0.36
    、
    0.36
    POSITIVE LOGITS
     analysed
    0.43
     എന്നീ
    0.41
    सरकारी
    0.40
    ೩
    0.40
    notebook
    0.40
    ઉસ
    0.39
    liberal
    0.38
    NaF
    0.38
    진
    0.38
    améli
    0.38
    Act Density 0.000%

    No Known Activations