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

    Neuronpedia

    INDEX
    Explanations

    Meta and companies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     over
    0.64
     weekend
    0.63
     Iran
    0.60
    Weekend
    0.59
     two
    0.58
     Times
    0.58
     H
    0.57
     aftermarket
    0.57
     China
    0.57
     analysis
    0.56
    POSITIVE LOGITS
    有害
    0.55
    Empleado
    0.55
    acchati
    0.53
    homotopic
    0.52
    кнове
    0.52
    udukan
    0.51
    ük
    0.50
     homeomorphic
    0.50
    بية
    0.50
    alag
    0.49
    Act Density 0.024%

    No Known Activations