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

    Neuronpedia

    INDEX
    Explanations

    foreign language and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ০
    0.55
    ⟹
    0.53
    ࿐
    0.52
    ]}\
    0.51
    とにかく
    0.51
     хорошие
    0.51
    ことにより
    0.51
    $.\
    0.51
     AIAA
    0.50
    ραι
    0.50
    POSITIVE LOGITS
     on
    0.54
     in
    0.53
    in
    0.52
    0.50
     porte
    0.47
    ين
    0.46
     bedrijf
    0.45
    سل
    0.45
    ية
    0.44
    폴
    0.44
    Act Density 0.000%

    No Known Activations