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

    Neuronpedia

    INDEX
    Explanations

    missing values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jantar
    0.81
     Dadurch
    0.71
     Payload
    0.67
     svojoj
    0.67
    Jogador
    0.66
    steuerung
    0.64
     Ausbildung
    0.64
    Projectile
    0.64
     kojim
    0.64
     Anleitung
    0.63
    POSITIVE LOGITS
     consolid
    0.86
     gaps
    0.75
     or
    0.75
     consolidation
    0.69
     consolidating
    0.69
     records
    0.68
     misrepresented
    0.67
     obligations
    0.66
     vacancies
    0.66
     বা
    0.66
    Act Density 0.023%

    No Known Activations