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

    Neuronpedia

    INDEX
    Explanations

    left followed by opening bracket

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    otek
    0.40
     sanctity
    0.40
     സെക്ര
    0.40
     outcrops
    0.40
    रत
    0.40
     Neend
    0.40
    esquerdo
    0.39
     timescale
    0.37
     diciendo
    0.37
    anking
    0.37
    POSITIVE LOGITS
    \{
    0.56
    [\
    0.49
    \{\
    0.48
    (\
    0.46
    <td>
    0.46
    (
    0.43
    [(
    0.42
    *{
    0.41
    ((
    0.40
    Ή
    0.40
    Act Density 0.001%

    No Known Activations