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

    Neuronpedia

    INDEX
    Explanations

    optimization and programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    et
    0.76
    า
    0.56
    ok
    0.55
    orrh
    0.53
    능
    0.52
    at
    0.51
    an
    0.51
    forth
    0.49
    ie
    0.49
    logical
    0.48
    POSITIVE LOGITS
    𝒔
    0.57
    <unused506>
    0.53
    <unused1076>
    0.53
     sujet
    0.51
    চন্ত্র
    0.51
     ASEAN
    0.51
    <unused632>
    0.51
    गोरि
    0.50
    ⬥
    0.49
    㬰
    0.49
    Act Density 0.151%

    No Known Activations