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

    Neuronpedia

    INDEX
    Explanations

    <

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Declined
    0.74
     Distress
    0.69
     приступи
    0.69
     പ്രസി
    0.68
     Anlagen
    0.68
    Protect
    0.67
     iPads
    0.67
     Deut
    0.66
    缬
    0.66
    Specular
    0.65
    POSITIVE LOGITS
     store
    0.64
    形で
    0.62
     मछ
    0.62
     ይመ
    0.62
     đứa
    0.61
     inform
    0.61
    inform
    0.61
     dressed
    0.61
     uf
    0.60
    giers
    0.60
    Act Density 0.004%

    No Known Activations