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

    Neuronpedia

    INDEX
    Explanations

    inherently involves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    E
    0.59
    G
    0.56
    r
    0.55
    0.55
    d
    0.54
    www
    0.54
    g
    0.54
      
    0.52
    The
    0.52
    th
    0.50
    POSITIVE LOGITS
     mauvaise
    0.55
     malzeme
    0.52
     idee
    0.51
     derniers
    0.50
     semblable
    0.50
    ಬ್ಬಿಣ
    0.50
     Worker
    0.49
     mauvais
    0.49
     scolaire
    0.49
     pracov
    0.48
    Act Density 0.007%

    No Known Activations