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

    Neuronpedia

    INDEX
    Explanations

    destination and description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DOL
    0.41
     రాజకీయ
    0.41
     politiques
    0.38
     DOL
    0.38
     부족
    0.37
     dotenv
    0.37
    రం
    0.37
     полити
    0.37
    Dol
    0.37
    Neg
    0.36
    POSITIVE LOGITS
     McKenna
    0.41
     Arsenal
    0.40
    ançois
    0.39
    irteenth
    0.39
     Libertad
    0.39
    GAIN
    0.39
     pendent
    0.38
     liberty
    0.38
    Arsenal
    0.38
     importantly
    0.37
    Act Density 0.001%

    No Known Activations