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

    Neuronpedia

    INDEX
    Explanations

    searching and listening

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =
    0.64
    '=
    0.52
    =\
    0.48
    byId
    0.48
    heroku
    0.46
    tych
    0.44
    :
    0.44
    arsipkan
    0.44
    abil
    0.43
    <td>
    0.43
    POSITIVE LOGITS
     Don
    0.46
     ecuaciones
    0.44
    澥
    0.43
     Shakespeare
    0.43
    녔
    0.42
    𝐞
    0.42
     Brock
    0.40
     You
    0.40
     don
    0.40
    लिसिस
    0.40
    Act Density 0.001%

    No Known Activations