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

    Neuronpedia

    INDEX
    Explanations

    Laws and constitutions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blunt
    -0.07
     oli
    -0.06
    .fold
    -0.06
     Defensive
    -0.06
    民主
    -0.06
    -free
    -0.06
    ​
    -0.06
     cultivated
    -0.06
    간
    -0.06
     On
    -0.06
    POSITIVE LOGITS
    uş
    0.06
    aler
    0.06
    nement
    0.06
     OnInit
    0.06
    	str
    0.06
    ochen
    0.06
     país
    0.06
     организации
    0.06
    ichern
    0.06
    ační
    0.06
    Act Density 0.044%

    No Known Activations