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

    Neuronpedia

    INDEX
    Explanations

    URL

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    0.82
    {~
    0.76
    in
    0.74
    ডি
    0.70
    पणा
    0.70
    ת
    0.69
    নিতে
    0.68
    ES
    0.67
    ট
    0.67
    ad
    0.67
    POSITIVE LOGITS
    евич
    0.84
     दूसरे
    0.77
    \})
    0.76
    shear
    0.75
    場所に
    0.71
    <%=
    0.70
     সাথে
    0.70
     healed
    0.68
     बार
    0.67
     embodied
    0.65
    Act Density 0.137%

    No Known Activations